GetRegisters: free source-backed practitioner tools

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds genuinely new behavioral context in the cost-domain exclusions and the eligibility precondition. It still omits what the comparison returns and whether the 'scope_confirmed' gate blocks execution.

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 short sentences, no filler, with the core action front-loaded and constraints following. Sizing is appropriate for the tool's modest complexity.

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?

Read-only with no output schema, so the description need not explain returns, but it leaves the required 'scope_confirmed' parameter unaddressed and gives no sense of the output shape (per-scenario funding figures vs. a diff). Adequate coverage of scope, incomplete on invocation mechanics.

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 carry parameter meaning. It does explain the scenarios array cardinality ('one or two', matching maxItems 2) and implies 'as of' currency, but the gating parameter 'scope_confirmed' is never explained, leaving a required boolean fully opaque.

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?

States a specific verb (compare) and resource (post-2023 new-build SDA funding scenarios), which is enough to separate it from get_ndis_sda_options at a glance. It does not explicitly name that sibling or state the boundary between listing options and comparing them, so it stops short of a 5.

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?

Gives clear applicability ('post-2023 new-build', 'one or two' scenarios) plus a hard precondition (all residents SDA-eligible) and explicit exclusions (rent, support services, vacancies, individual eligibility decisions). It lacks any when-to-use-this-instead-of-get_ndis_sda_options statement, so it is strong context without explicit routing.

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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real context beyond them: 'source-validated' (data provenance/freshness) and 'no account required' (auth profile). It does not mention caching or rate behavior, but that is minor for a zero-param read.

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 short clipped sentences, front-loaded with the resource and followed by the cost/auth fact. No 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?

For a zero-parameter, read-only, open-world lookup with no output schema, the description covers purpose plus the key cost/auth facts an agent needs before calling. Its only gap is routing relative to compare_ndis_sda, which the description ignores.

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 takes no parameters, so the schema has nothing to document and there is no parameter semantic burden to compensate for. Baseline 4 applies.

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?

States a clear verb ('Get') and a specific resource ('SDA building, design and SA4 choices'), and 'source-validated' signals data quality. It is distinguishable from the sibling compare_ndis_sda, though the SDA-domain jargon ('SA4 choices') keeps it from being fully self-explanatory.

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 only usage context is a precondition ('Free; no account required'). There is no statement of when to call this vs. compare_ndis_sda, which is the obvious sibling, and no indication of what the agent should do with the result.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered. The description adds value by stating what is returned (input choices, scope, citations), which matters since there is no output schema, but it omits error behavior for an unknown tool_id and does not say the data is read live.

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 compact sentence with the payload front-loaded and no filler. It is slightly dense, packing three distinct return categories into a single phrase, but nothing is wasted.

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 one-parameter read-only lookup with no output schema, the description conveys the return contents adequately, but it leaves the agent without guidance on how to obtain a valid tool_id or what happens on an invalid one.

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% and the single parameter 'tool_id' is a bare string with no format, source, or example. The description's 'for a free practitioner tool' only obliquely implies the parameter identifies a tool, so it does not compensate for the missing schema 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?

The description gives a specific verb ('Get') and enumerates the payload: current input choices, supported scope, and official citations for a practitioner tool. It is distinguishable from list_practitioner_tools and run_practitioner_tool by describing a metadata lookup rather than enumeration or execution, though it never names those 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?

There is no explicit when-to-use statement, no prerequisite (e.g. that the tool_id comes from list_practitioner_tools), and no indication of when to prefer this over run_practitioner_tool. Usage must be inferred entirely from the tool name.

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 annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered elsewhere. The description does add context beyond the annotations by noting the account-authorization requirement and clarifying that both free and paid subscriptions are returned, but it offers no detail on result shape or ordering.

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?

A single sentence that front-loads the resource read and then the authorization prerequisite. 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?

For a parameterless read tool with no output schema, the description conveys the resource scope and the auth gate, which is enough to invoke it correctly. It could be slightly richer, but nothing essential is 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?

The tool takes zero parameters, which matches the baseline of 4 for parameter semantics. There is nothing further the description could clarify about inputs.

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?

States a specific verb ('Read') and a well-defined resource ('connected free and paid subscriptions'), so an agent knows exactly what data is returned. No sibling tool overlaps this domain (the others cover NDIS, PFAS, packaging EPR, registers, and practitioner tools), so differentiation is unnecessary rather than missing.

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 prerequisite 'requires account authorization' implies an auth-gated read context, which is useful usage guidance. However, there is no explicit when-to-use, when-not-to-use, or alternative routing, leaving usage to inference.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, so the safety profile is covered structurally. The description adds the useful 'no account required' and 'source-backed' context, which is real value beyond the annotations, though it says nothing about pagination or result volume.

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 short, front-loaded sentences with no filler; the resource being listed comes first and the accessibility caveat second.

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 zero-parameter read-only list tool this is close to sufficient, but with no output schema the description could say something about what each listed tool entry contains or how many results to expect.

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 takes zero parameters, so per the rubric the baseline is 4. There is no parameter semantics work for the description to do.

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?

States a specific verb ('List') and resource ('practitioner tools') with the qualifying attributes 'free' and 'source-backed'. It is clear what the tool returns, but it does not distinguish itself from siblings like get_practitioner_tool or run_practitioner_tool.

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 phrase 'No account required' hints at accessibility but does not tell the agent when to use this listing versus get_practitioner_tool or run_practitioner_tool. No exclusions or alternatives are named.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds only the citation directive, which is useful but does not disclose return format, pagination, or auth requirements.

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 very short sentences and front-loads the resource before the citation directive. It is appropriately sized, though the first sentence's noun-phrase form leaves the action implicit.

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 no output schema, the description should explain what the tool returns or what the registers contain, but it does not. For a discovery tool with siblings like read_register, the lack of return-value or differentiation context is a significant gap.

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 takes zero parameters, so the schema is trivially complete and the description has no parameter semantics to explain. Baseline for zero parameters is 4.

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 phrase 'Available obligation registers' names the resource but lacks a clear verb, so the agent must infer that this is a list operation. The resource is specific enough to distinguish from read_register at a high level, but the purpose is only vaguely stated.

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?

'Cite original source URLs' is an output-handling instruction, not guidance on when to use this tool versus alternatives like read_register or compare_ndis_sda. No when-to-use or when-not-to-use context 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), so credit goes to genuinely additive context: it discloses the licensing/auth model ('Free; no account or subscription required') and an important scope boundary (no individual waiver determination is inferred). It stops short of describing what the plan output or date computation looks like.

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 short sentences, purpose front-loaded, with the licensing note and the waiver caveat each earning their place. No filler or restatement of the title.

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 regulatory-deadline planning tool with no output schema and zero schema descriptions, the definition leaves real gaps: it does not say what the plan returns (computed dates?), how the enums affect the result, or when denial_notice_date matters. The waiver caveat helps, but an agent still cannot predict the response shape.

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 carry the burden, and it only partially does. 'Self-attest coverage and extension/waiver status' maps loosely onto scope_confirmed, extension_status, and waiver_status, but it never explains the enum values (e.g. 'unknown' vs 'requested') or the role of the optional denial_notice_date.

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?

Names a specific verb+resource combination ('Plan Minnesota PFAS initial product-reporting dates') and even cites the authoritative source ('reviewed current MPCA guidance'). It is trivially distinguishable from siblings (NDIS SDA, UK packaging EPR, register/record tools), though it never explicitly contrasts itself with any of them, which keeps it just short of a 5.

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 states what the tool does not do ('an individual waiver determination is not inferred') but gives no positive when-to-use guidance, no prerequisites, and no alternatives. An agent must infer from the name alone that this is the tool to call for Minnesota PFAS date planning rather than, say, a general register reader.

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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety bar is low. The description adds genuinely useful context beyond them: cost/auth profile ('Free; no account or subscription required'), the self-attestation nature of the input, and an output caveat that it is not an eligibility determination or full cost figure.

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 tight sentences with the purpose front-loaded, followed by cost/auth details and a scope caveat. Every clause earns its place and nothing is padded.

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 7 required, undocumented parameters and no output schema, the definition leaves significant gaps. It does not explain how the enum inputs (activity, registration_route, approved_person_status) or the boolean flags shape the resulting plan, which is essential for a caller to supply correct inputs.

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% across 7 required parameters; the schema only supplies enum values with no explanations. The description touches the classification concept via 'Self-attest producer classification' but says nothing about is_group, is_marketplace, is_closed_loop, registration_route, or approved_person_status. With the schema silent, the description fails to compensate.

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?

States a specific verb ('Plan') on a specific resource ('2027 UK packaging EPR large-producer registration'), explicitly sourced from reviewed official guidance. The domain is immediately distinguishable from every sibling tool (NDIS, PFAS reporting, registers, practitioner tools). An agent can tell what this produces without opening the schema.

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?

Usage is implied by the domain ('Plan 2027 UK packaging EPR ... registration') and the clause 'the answer is not an eligibility determination or total EPR cost' sets a partial scope exclusion. However, there is no explicit when-to-use vs. when-not, no named alternative, and no prerequisite 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?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so safety is covered. The description adds useful scope context — results are limited to the current record and gated by an existing subscription, with no purchase or history returned — but stays vague about what 'subscription' enforcement means in practice.

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 tight sentence with the core action front-loaded and constraints trailing. No filler, though the trailing clause is somewhat cryptic rather than informative.

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?

No output schema exists, so the description could clarify what 'record details' returns, but it stays at 'current record details.' For a single-parameter read tool with strong annotations, the basics are covered, but parameter meaning and output expectations remain thin.

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% and the sole parameter record_id is left completely unexplained by both schema and description. The description does not clarify the expected identifier format or source, so it fails to 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 states a specific verb and resource ('Read current record details'), and adds scope qualifiers ('current', 'no purchase or history'). It does not differentiate itself from nearby siblings such as read_register or search_record_previews, so an agent cannot easily tell which read-path to pick.

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 a precondition ('according to your existing subscription') but gives no explicit when-to-use guidance and names no alternative. With siblings like search_record_previews and read_register available, the absence of routing guidance is a real gap.

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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description still adds real behavioral value: the free tier returns only the latest three records, and the archive and full fields are gated behind PRO access, which materially changes what an agent receives.

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 short, front-loaded sentences with no filler. It is efficient, though extremely sparse for a tool whose resource and parameter are both unexplained.

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 no output schema, the description does partially cover return semantics (latest three / full fields for PRO). But it leaves the required feed_id and the nature of a 'register' vs a 'record' undefined, which are essential for correct invocation.

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% and the single parameter feed_id is documented nowhere. The description never mentions feed_id, its format, or where it comes from, so it fails to 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 verb 'Read' and the resource 'register' are present, but the description actually describes the free-tier output ('latest three records') rather than what the tool retrieves. It does not distinguish this from the sibling read_record or list_registers, so an agent cannot confidently separate the register read from the record read without opening 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?

There is no when-to-use guidance and no named alternative among the many siblings (list_registers, read_record, search_record_previews). The 'Scoped PRO access' sentence is an upsell/limitation note, not guidance on when this tool is the right choice.

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?

Annotations already cover readOnly, idempotent, openWorld, and non-destructive behavior. The description adds useful behavioral context beyond annotations: free to run, no account required, and source uncertainty causes the tool to refuse an answer, signaling a failure/abstention mode.

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 tight sentences, front-loaded with the action and prerequisite, then the key behavioral caveat. Every clause earns its place with no filler 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?

No output schema exists, so the description could say what a successful run returns, but it does not. It also omits where to find tool_id and how the nested inputs object should be shaped, leaving meaningful gaps for an agent to infer.

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 carry the burden. It explains that inputs come from get_practitioner_tool, which helps for one parameter, but tool_id's format/source is undocumented and the nested inputs object structure is left entirely unspecified.

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?

States a specific verb (Run) and resource (practitioner tool), and distinguishes itself from the sibling get_practitioner_tool by naming it as the source of inputs. The phrase 'practitioner tool' is domain-specific but clear in context; no misleading 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?

Explicitly gives the prerequisite: inputs come from get_practitioner_tool, and notes no account is required. It provides clear context for use but does not state when-not to use it or name alternatives like list_practitioner_tools.

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?

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description adds genuinely useful behavior: it never spends money, and it returns purchase offers and coverage links. This cost and return-content disclosure goes beyond what the annotations convey.

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 short clauses, front-loaded with what it does, followed by return content and the purchase caveat. No filler, every sentence earns its place.

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 annotations covering the safety profile and no output schema, the description's coverage of return content and cost is adequate. But the complete absence of parameter guidance and pagination behavior for a four-parameter tool leaves a real gap.

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% across four parameters (limit, offset, search, feed_id), and the description provides no parameter semantics at all. limit/offset pagination and the meaning of feed_id are left entirely 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?

States a specific verb and resource ('search across current and archived record previews') with clear scope. It implicitly separates itself from read_record via the 'previews' concept, but does not name or contrast any sibling explicitly.

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 clarifies that this is a free search and that purchasing requires a separate spending-limited local client, which is useful routing. However, it gives no guidance on when to prefer this over read_record or other search siblings, leaving the primary when-to-use question inferred.

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