taxsort-mcp

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must carry full behavioral disclosure. It notes the operation is free and requires authentication (dpop_token), but does not explicitly state it's read-only or mention side effects. Given zero annotation support, more detail on safety (e.g., 'this tool does not modify any data') would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a brief overview, bullet-style return list, notes on cost and requirement, and clear parameter documentation. It is appropriately sized but could trim redundant phrasing (e.g., 'at this operator').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the existence of an output schema, the description adequately explains the return contents (purchase history, credit tranches, usage breakdown, logs). It covers authentication requirements and cost, providing sufficient context for an agent to decide and use the tool. Minor gap: no description of output format or pagination.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description fully compensates. It explains npub as Nostr public key, dpop_token as kind-27235 event, and days as number of days with default 30. While not exhaustive (e.g., no range for days), it adds meaningful context beyond the schema types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Generate a patron's account statement at this operator' with a specific verb and resource. It lists the contents (purchase history, credit tranches, usage breakdown, logs) and distinguishes from the operator's Authority tax balance, which differentiates from sibling tools like taxsort_check_balance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: it's free, requires npub ownership proof, and is for the patron's spending account. It implies usage for detailed statement retrieval, but does not explicitly exclude alternatives like taxsort_check_balance or taxsort_account_statement_infographic. Lacks 'when not to use' guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses output format, components, cost (1 api_sat), and proof verification process. Does not explicitly state side effects but as a read-only infographic generation, it's adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured: purpose, output summary, cost note, parameter list. Every sentence adds value, no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, description covers tool purpose, parameters, cost, and proof verification. No missing critical information for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has no descriptions (0% coverage), but description explains each parameter in detail: npub as Nostr public key, dpop_token as signed event, days with default. Adds significant meaning beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool generates an SVG infographic of an account statement, distinguishing it from the sibling taxsort_account_statement which likely returns raw data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Indicates this tool returns the same data as account_statement but in SVG format, implying a choice based on output preference. Costs and proof verification are noted but no explicit when-not-to-use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the tool is 'Free' and 'Polls the Authority MCP-to-MCP', which gives some behavioral context, but does not disclose whether it is idempotent, safe (read-only), or if authentication is needed. More detail on side effects or safety would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences long, front-loaded with the main action, and every sentence provides value. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values are covered. However, the description does not differentiate this tool from similar sibling tools (e.g., taxsort_get_operator_onboarding_status), and leaves 'dpop_token' unexplained. Adequate but not fully complete given the sibling context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 2 parameters with 0% description coverage. The description explains 'authority_npub' as the chosen Authority, adding meaning beyond the raw schema, but does not mention 'dpop_token' at all, leaving it undocumented. Partial compensation for one parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Check' and the resource 'adoption-request status at a chosen Authority', with explicit possible statuses. It distinguishes from siblings like taxsort_request_adoption (which submits requests) and taxsort_get_operator_onboarding_status (a different status check).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when wanting to know the adoption request status, but does not explicitly state when not to use it or provide comparisons to alternative sibling tools. The mention of polling gives some usage context but no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It does not disclose side effects (e.g., whether classifications are permanently modified, if the operation is reversible, or if it requires special permissions). The verb 'apply' implies mutation, but details are lacking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, but it sacrifices important details. It is front-loaded with the action, but could be restructured to include more context without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema, but its nature is unknown. The description omits what happens after rules are applied (e.g., returns a count, updates the session, etc.). For a mutation tool with no annotations, this is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%. The description does not explain any parameters beyond the schema. For example, it doesn't clarify that session_id identifies the target session or that npub is used for billing authentication.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Apply rules') and scope ('to unclassified transactions in a session'). It distinguishes from sibling tools taxsort_get_rules, taxsort_save_rule, taxsort_count_rule_matches, etc., which manage or count rules rather than execute them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as taxsort_count_rule_matches (for previewing matches) or taxsort_clear_transactions. No prerequisites (e.g., session must exist, rules must be defined) are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No behavioral traits disclosed. Description does not indicate whether the tool is read-only, requires authentication (npub is required but not mentioned), consumes credits, or produces any side effects. With no annotations, the description carries full burden but fails to provide transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, very concise. No wasted words. However, it is too brief and could be expanded to include key details without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Completely inadequate given tool complexity (5 parameters, no annotations, low schema coverage). Fails to explain output, billing requirements, or any context for effective usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (20%) and description adds no parameter-level information. It does not explain what 'question' should contain or the role of other parameters like 'history' or 'session_id'. The description relies solely on the schema, which is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('Ask') and the resource ('Financial Advisor about using TaxSort'). It distinguishes from sibling 'taxsort_ask_tax_researcher' by specifying 'Financial Advisor'. However, it could be more precise about the scope of questions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'taxsort_ask_tax_researcher'. The description does not specify prerequisites, context, or intended use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It only states the purpose but does not disclose side effects, authentication needs, or response behavior. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise, but it lacks structure for key details. It is appropriately sized for the minimal information provided but could be more informative without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description is incomplete given 5 parameters and a large sibling set. It does not explain the required question parameter or differentiate from similar tools, leaving the agent with insufficient context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (npub described in schema). The tool description adds no parameter information beyond the schema. With low coverage, the description fails to compensate for undocumented parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool asks a Tax Code Researcher about IRS provisions, with a specific verb and resource. However, it does not distinguish from sibling tool taxsort_ask_advisor, lacking differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, no context on appropriate question types, and no exclusion criteria. The description provides implied usage only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that the tool returns sats, is free, and explains the operational consequence of zero balance. Side effects and authentication needs are not mentioned, but given the tool's simplicity (read-only check), it is adequately transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the main purpose in the first sentence, followed by concise, essential details. Each of the four sentences adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no inputs, output schema exists), the description fully covers what the tool does, when to use it, and the consequence of zero balance. No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist (empty input schema). Schema coverage is 100%, so the description need not add parameter info. Baseline for zero parameters is 4. Description adds no confusion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb and resource: 'Check this operator's tax balance at the Authority.' It specifies the balance is for certifying patron credit purchases, distinguishing it from similar tools like taxsort_check_balance by emphasizing it's the operator's own funding, not a patron balance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: use to check available sats before certifying patron top-ups, and when balance reaches zero, must call purchase_credits instead. Also clarifies it's not a patron balance, steering users away from confusing it with other balance checks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses key behaviors: it checks a patron's credit balance, is free, and requires a dpop_token proving ownership. This covers safety and prerequisites adequately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a clear summary, explanatory details, and structured args. Every sentence adds value, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description covers purpose, differentiation, preconditions, and parameters well. It could mention potential errors or format of balance, but remains largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description explains both parameters: 'npub' as Nostr public key and 'dpop_token' as a kind-27235 Nostr event for proof, adding context beyond the schema's type-only definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Check a patron's credit balance at this operator' with specific verb 'check' and resource 'patron's credit balance'. It distinguishes from 'authority_check_balance' for operator's own balance, providing clear differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly contrasts with the sibling 'authority_check_balance' for when to use each. It also notes the tool is free and requires proof of npub ownership, offering practical usage constraints.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses the tool is free, requires npub proof for anti-front-running, and explains the reason. It does not explicitly state idempotency or side effects, but the read-like nature is implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured: purpose, usage instruction, cost/requirements, then parameter details. Every sentence adds value with no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 params, presence of output schema, and no annotations, the description covers when to call, parameter details (including reason for npub), and cost transparency. Output is left to schema, which is appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the Args section provides thorough explanations: invoice_id links to purchase_credits, npub specifies format, dpop_token describes the event type. Adds significant meaning beyond the schema's plain strings.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Check the payment status of a Lightning invoice', specifying a concrete verb and resource. It also links to purchase_credits, distinguishing it from sibling tools like taxsort_check_balance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Call after paying the invoice from purchase_credits', providing clear context on when to use. Does not mention alternatives or exclusions, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool is free, shows base cost and constraint effects, and implies it is read-only (preview). It does not contradict any annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the primary purpose, followed by a concise Args section. Every sentence adds value, and there is no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters (1 required, 0% schema coverage, no annotations, but has output schema), the description covers the key parameters adequately but omits explanation for npub and dpop_token. Overall, fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must compensate. It explains tool_id (UUID or capability string) and tool_kwargs (optional JSON for pricing preview) well. However, npub and dpop_token parameters are not explained, leaving gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Preview the effective cost of a tool call,' which is a specific verb and resource. It distinguishes itself from sibling tools like taxsort_check_balance, taxsort_check_payment, etc., which all have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: it's for previewing cost before a tool call and notes it's free (no credits required). However, it does not explicitly mention when not to use this tool or provide alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description covers behavioral traits: free, no side effects, no cache eviction, no relay touching. Could detail auth requirements or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with front-loaded purpose, code formatting, and separated args. Slightly verbose but efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool and presence of output schema, the description fully covers purpose, usage, side effects, and parameters, making it self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description adds meaning to both parameters (format hints, source of dpop_token) beyond the minimal schema, compensating for 0% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks dpop_token validity, differentiating it from sibling tools like request_npub_proof by framing it as a pre-validation step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use (before paid calls to avoid wasted credits) and compares to check_oauth_status, but lacks explicit when-not-to-use scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral traits. It only says 'check if the unlock response is valid' without disclosing idempotency, state changes, or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is overly minimal (one sentence) at the expense of necessary detail. It does not earn its place as it fails to inform the agent adequately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description does not connect to what 'valid' means. It is incomplete for effective decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only npub described). The description adds no information about parameters like 'response' or 'dpop_token', which remain undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'check' and resource 'unlock response', indicating the tool validates a response. However, it lacks specificity about what 'valid' means and does not distinguish it from sibling tools like 'taxsort_request_unlock'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool instead of alternatives. The context of many sibling tools, particularly 'taxsort_request_unlock', suggests a sequencing relationship, but this is not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for behavioral transparency. It states the destructive action (delete) but omits details about irreversibility, authorization requirements, idempotency, or confirmation steps. The output schema exists but its content is unknown; the description does not mention what the tool returns or any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and front-loaded. However, it is too brief; it could include more useful information without becoming verbose. It earns its place but leaves gaps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the existence of an output schema, return value details are less critical, but the description lacks context on prerequisites, side effects (e.g., cascading deletions), and how this tool differs from siblings like taxsort_delete_account_transactions. With low schema coverage, the description should compensate but does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (33%), and the tool description does not add meaning beyond the schema. The only parameter mentioned implicitly is 'session_id' via the word 'session', but no details on format, validity, or default. The npub and dpop_token parameters are not clarified in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it deletes all transactions and classifications for a session, with the explicit purpose of allowing CSV re-import. The verb 'delete' and resources 'transactions and classifications' are specific. However, it does not explicitly differentiate from similar sibling tools like taxsort_delete_account_transactions or taxsort_reset_classifications, though the name and scope suggest session-level bulk deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear usage hint ('so CSVs can be re-imported'), implying it is used when re-importing is needed after clearing data. However, it offers no when-not-to-use guidance, no mention of prerequisites (e.g., session must exist), and no comparison to alternative tools for more granular deletion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It indicates a read-only, non-destructive operation ('live preview') but lacks details on permissions, side effects, or output behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence. It is concise but perhaps too brief, lacking additional context that could fit without verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, low schema coverage, and no annotations, the description is insufficient. It does not explain 'rule pattern', matching logic, or output format (though output schema exists).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17% (only npub described). The tool description adds no information about the 6 parameters, including required fields like session_id and description_pattern, nor optional parameters like amount_value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Count how many transactions match a rule pattern (live preview)' uses a specific verb (count) and resource (transactions matching a rule pattern), clearly distinguishing it from sibling tools like taxsort_apply_rules (applies rules) and taxsort_get_rules (retrieves rules).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for previewing before applying rules, but does not explicitly state when to use versus alternatives, such as taxsort_apply_rules. No when-not or alternative tool guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It only says 'create' without disclosing behavioral traits like authentication requirements, rate limits, or potential side effects (e.g., creating a GitHub issue may have external consequences).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, to the point with no fluff. Could be slightly more structured but efficient for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists but no mention of return values. Tool has 6 parameters with only 17% schema coverage; description does not compensate. Lacks context on authentication, GitHub repository target, or rate limiting.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (17%), but description adds no parameter information beyond the schema's default values. The 'npub' parameter has a schema description but the tool description does not explain any parameter's semantics or usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Create a GitHub issue' with specific purposes (bug reports, feature requests, feedback), distinguishing it from the sibling tool 'taxsort_list_feedback_issues' which lists issues.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description includes the purpose but provides no when-to-use or when-not-to-use guidance. No explicit alternatives or exclusions, leaving the agent to infer from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description carries full burden but discloses no behavioral traits (e.g., billing, side effects, auth requirements). Minimal 'Create' is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise but under-specifies the tool. Loses points for being too brief to be effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Description fails to explain what a session is, usage context, or prerequisites. Given 4 parameters and many siblings, it is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (25%); description adds no meaning to parameters like label, tax_year, dpop_token. Does not compensate for missing parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Create a new TaxSort session for a tax year' using specific verb and resource. However, it does not differentiate from sibling tools like taxsort_get_session or taxsort_list_sessions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Missing context about prerequisites or sequence (e.g., must create session before other operations).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose behavioral traits such as authentication requirements, side effects (e.g., session modification), or potential errors. For a mutation tool, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that immediately conveys the action and purpose. It is front-loaded and efficient, though it could be slightly expanded without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters, an output schema, and no annotations, the description is too minimal. It does not explain what a share token is, how it works, or what happens when invoked. Parameter semantics and behavioral details are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (25%), and the tool description adds no information about parameters. The schema describes npub partially, but session_id, dpop_token, and expires_days are left undefined. The description does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (create) and resource (share token) with purpose (so another user can access this session). It is specific but does not differentiate from similar sibling tools like taxsort_create_session or taxsort_load_share_token.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. Sibling tools include taxsort_create_session (creates a session) and taxsort_load_share_token (loads a shared token), but the description does not provide context for when to choose this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The tool is destructive (deletes all transactions and classifications), but the description does not disclose potential side effects, reversibility, or authorization requirements. No annotations exist to compensate, so the description carries full burden and falls short.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise but missing critical details. While not verbose, it sacrifices completeness for brevity, resulting in an adequate but not optimal balance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a delete operation with multiple parameters and an output schema, the description is incomplete. It lacks behavioral details, parameter explanations, and any mention of output or error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only 'npub' has a description). The tool description adds no information about the parameters, such as what 'account' refers to or the purpose of 'session_id'. It fails to compensate for the low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('delete'), the resource ('all transactions and classifications'), and the scope ('for a specific imported account'). It distinguishes itself from sibling tools like 'delete_classification' which deletes a single classification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'clear_transactions' or 'delete_classification'. There is no mention of prerequisites, such as requiring an active session or account ownership.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It lacks details on what is removed (specific classification or all), reversibility, permissions, or side effects, leaving ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 9 words is concise but omits essential parameter guidance; could be improved without losing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with multiple parameters, the description is too minimal. It doesn't explain how to specify the classification to remove or the transaction context, despite having an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description adds no information about parameters. Schema has low coverage (25%), and description does not clarify the role of session_id, transaction_id, npub, or dpop_token.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action 'Remove a classification' and the effect 'reverting the transaction to unclassified', distinguishing it from siblings like save or reset classifications.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage for undoing a classification, but no explicit guidance on when to use vs alternatives like taxsort_reset_classifications, nor when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully bears the burden of behavioral disclosure. It transparently explains cascading deletion to patron redemptions and the no-op behavior for chain references, which are critical side effects. This is above average for a deletion tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with four sentences, each providing essential information. The main action is front-loaded, and there is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description does not need to detail return values. However, the lack of parameter explanations and the missing explanation of the 'dpop_token' field leave gaps. The cascading context is good, but completeness is average overall.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description does not explain the parameters. 'coupon_id' is somewhat obvious, but 'dpop_token' is not explained, and the mention of 'requires proof' is not directly linked to it. The description adds minimal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool deletes a coupon and details cascading effects. It uses a specific verb and resource. However, it does not explicitly distinguish from sibling tools like 'taxsort_forget_coupon' or 'taxsort_update_coupon', leaving some ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates the tool is restricted to operators and requires proof, providing some usage guidance. However, it does not specify when not to use the tool or mention alternatives, such as using 'taxsort_forget_coupon' for a softer removal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only says 'Delete' but does not explain if deletion is permanent, reversible, or requires special permissions. For a destructive operation, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no fluff. However, it is too brief and omits crucial information, but that is a completeness issue, not a conciseness one.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and multiple parameters, the description provides no context about what a custom category is, when deletion is appropriate, or what the response contains. It is grossly incomplete for effective tool use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not mention parameters at all. Schema coverage is low (33%) with only npub described. The required category_id lacks explanation of its meaning or how to obtain it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the verb and resource clearly: 'Delete a custom category.' It is specific enough to convey the action but does not differentiate from sibling delete tools like delete_classification or delete_rule.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. With many sibling delete tools, the description lacks context for correct selection, such as prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that the operation is a write to a sensitive credential vault, requires authentication via dpop_token, and is free. It does not mention reversibility or error conditions, but the sensitive nature and auth requirements are well-documented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief with a clear summary sentence followed by a structured argument list. Every sentence adds value, and the key behavior is front-loaded. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a delete operation with an existing output schema (not shown), the description adequately covers the input. It lacks explicit mention of return value or success confirmation, but given the tool's simplicity, this is minor. The context of it being a sensitive write operation is well-covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema provides no parameter descriptions (0% coverage). The description adds full semantics: npub as Nostr public key, dpop_token as a kind-27235 event, and field as the credential field name. This fully compensates for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool removes a single credential field, with the verb 'remove' and the resource 'patron credential field'. It distinguishes from sibling tools like 'update_patron_credential' and 'forget_credentials' by specifying field-level deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states it requires npub ownership proof via dpop_token and that it is a write operation to a sensitive vault. However, it does not explicitly contrast when to use this vs alternative tools like 'update_patron_credential' or 'forget_credentials'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must cover behavioral traits. It only states 'Delete' without describing side effects, authorization needs, or idempotency. The single sentence is insufficient for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise (one sentence), but at the cost of omitting crucial parameter context. It is neither well-structured nor front-loaded with the most critical information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with low schema coverage and no annotations, the description is incomplete. It fails to explain the required npub parameter or the optional dpop_token, and does not leverage the existing output schema to clarify return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only npub has description). The description does not explain the role of rule_id or dpop_token. It adds zero value beyond the parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (delete) and the resource (classification rule) with identifier method (by ID). It effectively distinguishes from sibling tools like taxsort_get_rules (read) and taxsort_save_rule (create/update).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., taxsort_save_rule for modification). No context on prerequisites or post-conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description fully carries the burden. It discloses key behaviors: the operation is cosmetic, the coupon persists, re-redeem is possible, and it requires npub proof. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary action. No filler, every sentence adds critical information (cosmetic, re-redeem, free, npub requirement).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, cosmetic nature, and reusability. Output schema exists but not shown; description does not explain return values. Missing explanation for 'dpop_token' parameter. Otherwise complete for a simple removal tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must compensate. It provides context for 'npub' (requires proof) but does not explain 'coupon_id' or 'dpop_token' parameters. Missing details reduce value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Remove' and resource 'coupon from this patron's redemption list.' It distinguishes itself from sibling tools like 'taxsort_delete_coupon' (deletes coupon entirely) and 'taxsort_redeem_coupon' by specifying it only removes from the list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Cosmetic only — the coupon itself still exists at the operator, and the patron can re-redeem the same code later.' Also provides prerequisite 'requires proof of npub' and that it is free.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description effectively communicates that deletion is destructive ("as destructive as a write") and requires authentication via dpop_token. This gives the agent a good safety understanding, though it omits details like idempotency or behavior on missing credentials.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is reasonably concise, with a brief introductory paragraph and a separate Args section for clarity. It avoids unnecessary repetition, though the word "forget" duplicates the tool name. Overall, it is well-structured and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 0% schema coverage and no annotations, the description covers the core behavior and parameters adequately but misses details like success/failure responses or prerequisites (e.g., credentials must exist). The presence of an output schema reduces the need to explain return values, but the description could still be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Since schema description coverage is 0%, the description adds meaningful context for all three parameters: service (credential service), npub (Nostr public key with format hint npub1...), and dpop_token (kind-27265 Nostr event). It explains their purpose beyond bare type information, e.g., the distinction between operator and patron npub usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (Delete vaulted credentials) and the resource (for a specific service and npub). It distinguishes from similar tools like taxsort_delete_patron_credential by covering both operator and patron credentials, but does not explicitly differentiate from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage context by explaining how to pass npub for operator vs patron credentials and emphasizes the need for proof of ownership. However, it lacks explicit guidance on when not to use this tool or alternatives, such as taxsort_delete_patron_credential for patron-only cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It describes a 'list' operation (read-only), but does not explicitly state safety, side effects, or requirements (e.g., session must exist). Minimal behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no fluff, clear and to the point. Excellent front-loading of core action and output.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values need not be elaborated. However, tool has 3 params (1 required) and no explanation of session prerequisites or how to obtain session_id. Adequate but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 33% schema description coverage (npub has description). The tool description adds no parameter meaning beyond the schema, missing chance to clarify session_id or dpop_token semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all accounts in a session with their types and transaction counts. This distinguishes it from siblings like taxsort_account_statement or taxsort_get_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage within a session via session_id, but no explicit guidance on when to use this versus alternatives (e.g., taxsort_get_account_statement). Lacks exclusions or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. It does not disclose whether the tool is read-only, any side effects, authentication prerequisites, or rate limits. The mention of npub for billing hints at authorization but is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no unnecessary words. It front-loads the core action and follows with a usage context, making it efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 7 parameters and no annotations, but the output schema exists. The description explains the duplicate detection context but lacks details on required session setup or the role of other parameters. It is adequate for a simple tool but not fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at only 14%, the description adds meaning for key parameters: amount, date, and days. However, it does not explain session_id, npub (though schema describes it), dpop_token, or exclude_id, leaving gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool does: 'Fetch transactions with the same amount within ±days of a date.' This is a specific verb+resource combination and clearly distinguishes it from sibling tools like taxsort_get_transactions which likely fetch all transactions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions it is 'Used by the classifier to detect duplicates from overlapping CSV imports,' providing a clear use case. However, it does not explicitly state when not to use this tool or suggest alternatives like taxsort_get_transactions for general queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must disclose behavior. It only states the tool 'gets' a key without mentioning side effects, sensitivity of the key, authentication requirements, or rate limits. The read-only nature is implied but not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise, but this brevity comes at the cost of completeness. The single sentence contains no wasted words, but structuring with separate sections for parameters and behavior would improve clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description fails to provide security context (e.g., that this key is sensitive and should be handled carefully) or any guidance on when to invoke this tool. The purpose is clear but incomplete for safe usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% (only npub has a description). The tool description adds no information about either parameter, leaving dpop_token completely undocumented. The description should clarify the role of dpop_token and the billing implications of npub.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool retrieves an 'Anthropic API key' for 'FE-driven classification'. Verb and resource are specific and distinguishable from sibling tools like taxsort_get_github_token.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The single sentence does not provide use cases, prerequisites, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description provides minimal behavioral insight. It fails to disclose whether the tool is read-only, requires authentication (despite npub parameter), or any side effects. No mention of rate limits or data freshness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (one sentence), but it sacrifices necessary detail. While brevity is good, it under-specifies key aspects, making it less useful. It could be expanded without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description does not clarify what 'aggregated' means (time period, scoping), or how it differs from similar tools. It is incomplete for a cost analysis tool among many siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (npub described). The description adds no value beyond the schema for npub, and none for dpop_token and session_id. It fails to compensate for the low coverage, leaving two parameters unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves aggregated API usage statistics for cost analysis. However, it does not distinguish from sibling tools like taxsort_get_import_stats or taxsort_report_api_usage which could have overlapping purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as taxsort_report_api_usage for reporting or taxsort_get_transactions for detailed logs. The description lacks context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only states 'Get', implying a read operation. It does not disclose any behavioral traits such as authentication requirements (despite npub being described as 'Required' in the schema, the schema itself lists no required parameters, causing inconsistency) or rate limits. The description adds little beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short (one sentence), which is concise, but it sacrifices necessary detail. It is front-loaded with the core action, but every sentence should add value; here the single sentence is minimal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and presence of an output schema, the description is insufficiently complete. It does not explain what custom categories are, how they relate to the user, or any prerequisites like needing an authenticated session. The description leaves important gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool description adds no information about parameters. Schema description coverage is 50% (only npub has a description, which is contradictory), and the tool description does not clarify the purpose or usage of npub or dpop_token. This leaves agents without essential usage context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'custom categories', making the basic purpose understandable. However, it does not differentiate from sibling tools like taxsort_save_custom_category or taxsort_delete_custom_category, so it lacks distinctiveness.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus other tools, no prerequisites, and no exclusions or alternatives mentioned. The description is too brief to inform decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries full burden. It states the token is for issue creation, implying a read-only operation, but doesn't disclose rate limits, token lifespan, or side effects. Acceptable for a simple retrieval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with purpose, no unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple token retrieval tool with an output schema. However, lacks usage guidance and parameter details, leaving some ambiguity for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% (only npub has a description). The tool description adds no additional meaning to parameters, leaving the dpop_token parameter completely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a GitHub token specifically for creating issues in the taxsort-mcp repo. This distinguishes it from other token-getting tools like taxsort_get_anthropic_key.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, no prerequisites or conditions mentioned. The description is purely declarative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries full burden for behavioral disclosure. It only states 'Get import statistics' without mentioning read-only nature, required permissions, side effects, or data scope. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise but under-specified. It lacks detail required for a usable tool description, making it borderline inadequate rather than efficiently concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present but not referenced, the description omits what the output contains or how it relates to the input. Given the simplicity of the tool, more context about expected use and return values is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (only npub has a description), and the description does not add meaning for session_id or dpop_token. No parameter details are provided beyond what the schema offers, failing to compensate for low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get', resource 'import statistics', and context 'for a session'. It distinguishes from sibling tools like taxsort_get_session (session info) and taxsort_get_summary (summary), but could be more specific about what constitutes import statistics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, prerequisites, or scenarios. The description does not address when to call this vs other get_* tools, leaving agents to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses behavior: returns latest metadata fields or empty profile, and states data is public with no side effects. This is transparent and adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, second adds return details. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one optional parameter and an output schema, the description covers purpose, return values, and fallback. Missing explicit parameter explanation but otherwise complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description implies the npub parameter but does not explicitly define its format or behavior when empty (default). Schema coverage is 0%, so description should compensate, but it only mentions 'an npub' without detailing the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Read' and the resource 'npub's public Nostr profile', specifying the NIP-01 kind-0 metadata. It distinguishes itself from siblings like taxsort_publish_nostr_profile by being read-only.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description notes 'Free, no proof — the data is already public on relays', indicating no authentication needed. It provides clear context for when to use the tool but does not explicitly mention when not to use or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses it generates a proof without side effects, but it does not mention idempotency, authorization requirements, or rate limits. The behavioral details are adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence followed by a bullet list of parameters. Every sentence earns its place; there is no redundancy or fluff. The structure is front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description is fairly complete: it explains the tool's core functionality and required inputs. It does not elaborate on cryptographic details or prerequisites, but the domain-specific context is sufficient for knowledgeable users.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It provides brief descriptions for both parameters (notarization_id and npub), adding context beyond the schema type definitions. However, the descriptions are minimal and could include more detail (e.g., expected formats).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a Merkle inclusion proof for a patron's balance in a Bitcoin-notarized snapshot. The verb 'Generate' and the specific resource 'Merkle inclusion proof' make the purpose distinct from siblings like taxsort_check_proof_status or taxsort_list_notarizations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used after a notarization to get a proof, but it does not explicitly state when to use it versus alternatives, such as check_proof_status or list_notarizations. No exclusions or alternative references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It clearly states it is a non-destructive report of configuration readiness. Could mention if any special permissions are needed, but the read-only nature is implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences; front-loaded with purpose, then additional details, then explicit sibling differentiation. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present, description needn't explain return values. It covers what the tool does, what it shows, and how it differs from related tools. Complete for a zero-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters (baseline 4). The description adds no parameter info, but no parameters exist so no additional detail needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it reports operator configuration readiness, showing configured and missing settings and how to deliver missing values. It explicitly distinguishes from the sibling tool get_patron_onboarding_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly directs when to use this tool versus the alternative: 'For patron-level credential status, use get_patron_onboarding_status instead.' It also notes it is free, implying no cost.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses key behaviors: never exposes values, requires proof of npub ownership, and notes the list is sensitive. It does not mention error handling or rate limits, but the core read-only nature and authentication requirement are transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two paragraphs plus a structured Args section. Every sentence adds value: main purpose, safety note, authentication requirement, and parameter details. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no annotations, output schema present), the description is complete. It covers purpose, parameter semantics, sensitivity, and authentication. The output schema handles return value details, so no need to describe them in the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (no parameter descriptions), but the description provides clear, specific explanations for both parameters: npub expects 'npub1...' format, dpop_token is a kind-27235 Nostr event signed by npub. This adds significant meaning beyond the schema's type-only definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists stored patron credential field names, not values. The verb 'list' and resource 'patron credential field names' are specific, and it distinguishes from sibling tools like taxsort_update_patron_credential by emphasizing it only returns field names.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explains when to use: to verify which fields are configured, and notes values are never exposed. It provides context about sensitivity and required proof of npub ownership. While it doesn't explicitly exclude alternatives, the purpose is distinctive enough among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool is free, requires specific authentication (dpop_token), and reports credential status differently for set-once vs. dynamic services. It does not explicitly state it is read-only or mention rate limits, but the name and context imply that. Overall, it provides substantial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, with a brief purpose statement followed by details on service types, prerequisites, and parameter descriptions. Every sentence contributes to understanding. It is front-loaded with the primary function and uses clear formatting.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has an output schema (reducing the need to describe return values), the description covers the essential aspects: purpose, authentication requirements, behavioral distinction between service types, and parameter definitions. It is contextually complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no descriptions for its two parameters (0% coverage). The description compensates by explaining patron_npub as 'The patron's Nostr public key (npub1...)' and dpop_token as 'A kind-27235 Nostr event signed by patron_npub for this tool.' This adds meaningful semantic context beyond the schema's type definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Report a patron's credential readiness for this operator.' It distinguishes between set-once and dynamic services, and mentions proof of npub ownership is required. The verb 'get' and the phrase 'credential readiness' make the function specific and differentiate it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use the tool (to check credential readiness) and prerequisites (proof of npub ownership via dpop_token). However, it does not explicitly mention when not to use it or compare it to alternatives like taxsort_get_patron_credential_fields. Nevertheless, the usage scenario is well-defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that it is free, self-initializes if no model exists, and that no economic data is from code. With no annotations, this provides adequate behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with main action. Every sentence adds value (purpose, cost, initialization behavior).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Fully adequate for a parameterless getter with output schema present. Provides all necessary context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters; schema coverage is 100%. Baseline score 4 as description adds no param info (not needed).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get the active pricing model for this operator', using specific verb and resource. Distinguishes from siblings like taxsort_set_pricing_model and taxsort_reset_pricing_model by being a getter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage: call when you need to know the current pricing model. No explicit alternatives, but simplicity of tool makes it obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully convey behavior. It does not disclose side effects, permissions, rate limits, or that this is a read-only operation. Minimal behavioral insight.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise at one sentence, but omits critical information. The structure is minimal and insufficient for an effective tool definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description fails to mention what the tool returns or how to use it. With 3 parameters and no elaboration, it is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (npub description in schema). Tool description adds no parameter explanations, leaving users uninformed about dpop_token and session_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('Get') and resource ('classification rules') and specifies scope ('for the current patron'). However, it does not differentiate from similar sibling tools like taxsort_get_custom_categories, but the name is specific enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives, prerequisites, or conditions. The description lacks any context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must fully disclose behavioral traits. The description merely states 'Get', implying a read operation, but does not confirm non-destructiveness, authentication needs (beyond npub), rate limits, or what happens if session_id is invalid. The behavioral disclosure is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is concise but under-specified. It conveys the basic action but lacks structure or detailed information that would aid an agent without adding significant length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 parameters, one required) and the existence of an output schema (though not shown), the description should provide more context about what 'details' and 'summary stats' are returned. It does not mention session status, creation time, or what stats are included, leaving the agent with incomplete information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (only npub has a description). The tool description adds no meaning beyond the schema; it doesn't explain the purpose of 'session_id' or 'dpop_token'. For the two undocumented parameters, the agent has no guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'Get' and identifies the resource as 'session details and summary stats', which is clear and distinguishes from siblings like 'taxsort_session_status' (likely status-only) and 'taxsort_list_sessions' (list all sessions). However, it lacks specificity on what 'details' includes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as 'taxsort_session_status' or 'taxsort_list_sessions'. There is no mention of context, prerequisites, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided; the description does not disclose whether the tool is read-only, requires authentication, or has other behavioral traits. The brief description leaves ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise but too brief, lacking necessary detail. It is front-loaded but at the expense of completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, an output schema, and many siblings, the description is incomplete. It does not explain the summary's structure, grouping behavior, or prerequisites like session_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 17% schema description coverage, the description should compensate but adds no meaning beyond the schema. Parameters like month, scope, group_by are unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves a grouped spending summary for tax reporting, but does not distinguish it from siblings like taxsort_get_transactions which also retrieve transaction data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like taxsort_get_transactions or taxsort_get_account_statement. No when-not or context provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. Description reveals LEFT JOIN behavior and pagination via unclassified_only. Does not cover other behavioral aspects like performance, side effects, or required permissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three clear, front-loaded sentences with no fluff. Each sentence adds value: purpose, join detail, usage tips.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite an output schema, the description omits many parameters and use cases. For a tool with 13 parameters, this lacks completeness for correct selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 8% of input schema parameters have descriptions. The description adds context for unclassified_only and date_from/date_to but leaves 11 of 13 parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states 'Get transactions for a session with optional filters' and mentions LEFT JOIN with classifications. Purpose is clear, but no explicit differentiation from sibling taxsort_get_transactions_paged.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides specific usage tips (unclassified_only for unclassified pages, date_from/date_to for date ranges). Lacks guidance on when not to use and alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It indicates server-side processing but does not disclose whether the operation is read-only, auth requirements (beyond npub), rate limits, or data constraints (e.g., max page size). For a read-like operation, these are critical gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, front-loaded with the main purpose. It is concise, though the second and third sentences could be merged. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 16 parameters and low schema coverage, the description is incomplete. It omits pagination details (page, page_size) and other filter parameters. The output schema exists, so return values are covered, but the tool's core functionality (paging) is not explained in text.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 6%, so the description must compensate. It adds meaning for group_sort, sort_col, sort_dir, and group_by, explaining their relationships. However, many parameters (page, page_size, month, search, account, etc.) remain unexplained, leaving the agent with incomplete understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides server-side filtered, grouped, sorted, paginated transactions, which is a specific verb+resource. However, it does not explicitly differentiate from the sibling tool 'taxsort_get_transactions', which likely lacks paging.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains how group_sort, sort_col, sort_dir, and group_by interact, giving some usage guidance. However, it does not specify when to use this tool over alternatives like taxsort_get_transactions, nor does it mention prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description only states the action but does not disclose side effects (e.g., data persistence), authentication requirements, error conditions, or any behavioral traits beyond the basic operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundant words. Purpose stated first, followed by key parameter clarifications. Efficiently communicates core information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters and low schema coverage, description lacks detail on import behavior (e.g., overwriting vs appending), output format (though output schema exists), error cases, and prerequisite sessions. Incomplete for a state-mutating tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (17%). Tool description clarifies that 'content' is raw CSV text and 'account_name' is optional overrides filename-derived account, adding value for 2 out of 6 parameters. However, leaves session_id, filename, npub, and dpop_token unexplained beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'Import' and resource 'CSV file into a session', clearly distinguishing it from siblings. It also notes that account_name overrides filename-derived account, adding precision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives (e.g., other import methods). No exclusions or context provided for usage decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description fully discloses that the tool is free and has no side effects. It also explains the invariant that tool_id stays constant while mcp_name may change, which is crucial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured, and front-loaded with the main purpose. Each sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description adequately covers purpose, behavior, and use case. It is complete for a simple lookup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so no additional description is needed. The description adds no parameter information, which is appropriate given 100% schema coverage and no required details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Return canonical (tool_id, mcp_name, …) for every registered tool.' This is a specific verb and resource, and the explanation that it is the authoritative source for tool identification distinguishes it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly identifies clients that need this tool (Studio, agents, FE) and explains its role in UUID-joining for reconcile. While it does not explicitly list when not to use it, the context and sibling differentiation provide sufficient guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses that the tool 'Returns the type, category, description, and parameter specs,' which indicates a read operation, but does not explicitly state non-destructiveness or other behavior. The 'Free' note hints at no cost, but more could be said about safety or permissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise, with three clear sentences: purpose, return details, and cost note. It is front-loaded and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and presence of an output schema, the description covers the essential purpose and return content. It is complete for a simple listing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, so schema description coverage is 100%. Per rubric, 0 params warrants a baseline of 4. The description adds no parameter information since none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all available constraint types and their parameter schemas,' specifying the verb (List), resource (constraint types), and what is returned (parameter schemas). It distinguishes from sibling list tools by focusing on constraint types with schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing to know constraint types for a pricing pipeline, but does not provide explicit guidance on when to use this tool versus alternatives or when not to use it. The note 'Free — no credits required' adds some context but not enough for clear differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full burden. It discloses that the tool lists coupons with a progress bar and is restricted to operators requiring proof. This gives good insight into behavior, though it could explicitly state that it's a read-only operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three concise sentences, each adding value: purpose, detail about returned data, and usage restriction. No redundant or unnecessary text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description sufficiently covers what each row contains (times_redeemed, progress bar) and the restriction. It could mention pagination or limits, but overall it's complete for a listing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'dpop_token' has 0% schema description coverage, and the description does not explain its purpose. The mention of 'requires proof' might imply it's used for authentication, but it's not explicitly linked.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (List), the resource (coupons), the scope (every coupon this operator has minted), and ordering (newest first). It distinguishes from sibling 'list_my_coupons' by specifying 'operator'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the restriction 'RESTRICTED to operator — requires proof', providing a condition for use. However, it does not explicitly state when not to use or suggest alternatives like list_my_coupons for non-operators.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It implies read-only behavior but does not disclose authentication requirements, side effects, or output format. The description is too sparse to ensure safe usage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single-sentence description is concise, but it may be too brief for a tool with no annotations. It front-loads the purpose but omits important details, making it minimally acceptable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and presence of an output schema, the description is adequate but lacks details on authentication, pagination, or filtering. It provides the core purpose but not a complete picture for unassisted selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 50% (npub has a description, dpop_token does not). The tool description adds no additional meaning beyond the schema; it fails to compensate for the undocumented dpop_token parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List'), the resource ('feedback issues'), and the scope ('submitted by this patron'). It effectively distinguishes the tool from its sibling 'taxsort_create_feedback_issue' which performs creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., other listing tools among siblings). There is no mention of prerequisites, context, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, but the description discloses that it is free, requires npub proof, and returns both active and exhausted redemptions with status field explanation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise paragraphs with front-loaded main purpose and no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple listing tool with output schema, it covers purpose, scope, and return format; could add pagination but not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description barely adds meaning; it mentions npub proof but does not explain the npub or dpop_token parameters beyond their existence.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and resource 'coupons this patron has redeemed on this operator', distinguishing it from sibling tools like taxsort_list_coupons.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies usage for listing a patron's redeemed coupons, but does not explicitly state when to use this vs alternatives like taxsort_list_coupons or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full responsibility. It only states it lists records with optional filters but does not disclose if it's read-only, requires authentication, how results are ordered, pagination, or what fields are returned. The output schema exists but is not described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short (two sentences plus arg list), front-loaded with the purpose, and contains no superfluous information. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and parameters are simple, the description is fairly complete for a list operation. However, it lacks behavioral context (e.g., authentication, rate limits, ordering beyond 'recent') and does not explain what the output contains. Adequate but with gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning to parameters beyond the input schema: 'limit' is explained as max records, 'status' is explained with examples. However, it does not specify allowed values for 'status' (only examples) or mention that default '' means no filter. Schema coverage is 0%, so description partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists recent Bitcoin notarization records. It uses a specific verb ('List') and resource ('Bitcoin notarization records'), distinguishing it from siblings like taxsort_notarize_ledger or taxsort_get_notarization_proof.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. No exclusion criteria or context for choosing between taxsort_list_notarizations and related tools like taxsort_get_notarization_proof.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description lacks disclosure of side effects, authentication requirements (beyond npub hint), rate limits, or credit costs. The npub parameter implies billing, but this is not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence, front-loaded with key information, no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values are handled, but missing pagination info, authentication details, and usage context. The tool is incomplete for an unfamiliar agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, and the description adds no meaning beyond the schema. The dpop_token parameter is unexplained, and the npub parameter's 'Required' hint is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists sessions owned by the current patron, using a specific verb and resource, distinguishing it from related tools like taxsort_get_session.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., taxsort_get_session), nor any context about prerequisites or limitations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It does not mention side effects, authentication requirements (e.g., npub for billing), or what happens on success/failure. The output schema provides some structure but is not referenced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (one sentence) and avoids fluff, which is positive. However, it is too brief, lacking any structure or detail that would aid understanding. It is not a tautology, so it meets the minimum.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description omits critical context such as error handling, token validity requirements, and whether the shared session is mutable. The tool's complexity is low, but the description fails to cover key aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (npub's description is a required note), and the tool description adds no information about the parameters. For low coverage, the description must compensate, but it does not explain share_token, dpop_token, or npub's role beyond billing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Load') and resource ('shared session via a share token'), which distinguishes it from sibling tools like create_share_token or get_session. However, it does not explicitly contrast with these siblings to achieve a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like taxsort_create_share_token or taxsort_get_session. The description lacks context on prerequisites (e.g., needing a valid share token) or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses authentication requirements, return value (new coupon row), and parameter constraints (e.g., discount_percent 0-100, operator-scoped uniqueness). No mention of side effects like rate limits, but the auth and uniqueness constraints are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main purpose and then lists parameters in a clear structure. It is informative without being overly verbose. Could be slightly more concise, but every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 params, mutating action) and the presence of an output schema, the description covers creation, auth, uniqueness, and return value adequately. It explains required vs optional parameters and their semantics, making it complete for an AI agent to use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description adds extensive meaning: it explains each parameter's purpose (e.g., 'catchy code patrons type to redeem', 'Percentage off the base price (0-100)'), defaults, and allowed values (null for unlimited). This goes far beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?