Receipt Audit

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

The description discloses high-value behavior that the annotations do not: a 1-credit cost with a refund when the file is unreadable, and an implicit persistence/duplicate-detection side effect (consistent with readOnlyHint=false). It also tells the agent the result includes reasons for AI/edit scoring.

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 core capability is front-loaded in one dense but well-structured sentence, with cost/refund as a distinct second sentence. It is long, but nearly every clause maps to a real user-visible behavior, so little 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 tool with an output schema, return values need not be explained; the description instead covers the input modes, billing, refund condition, duplicate check, and detection scoring. Nothing an agent needs to invoke it correctly 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?

Schema description coverage is 100%, so each parameter (api_key, image_url, mime_type, image_base64) is already documented and the baseline is 3. The description only restates the URL-vs-base64 duality and file types, adding no syntax or constraint detail 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 states a specific verb-and-resource with enumerated sub-operations: extract fields, check arithmetic/tax/dates, score edit/AI-generation signals, and duplicate-submission lookup. An agent can distinguish this from every sibling (create_api_key, create_claim_link, get_account, report_feedback) without opening a 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?

It gives clear triggering context (receipt/invoice verification) and acceptable inputs (image or PDF, https URL or base64), which frames when the tool applies. It does not name exclusions or alternative tools, but the sibling set is unrelated, so there is little genuine ambiguity to resolve.

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 it is a non-read-only, non-idempotent, non-destructive write. The description adds real behavioral context beyond that: the returned key carries 50 free checks, a claim_url enables a human to take over the account, and the key is reusable for all subsequent calls. It omits what happens on repeat invocation despite idempotentHint=false.

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, with the primary outcome (new API key) front-loaded and the follow-on mechanics (claim_url, reuse) after it. Every clause carries information and there is 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?

An output schema exists, so return-value enumeration is not strictly required, yet the description still conveys the meaningful parts (free checks, claim_url). With no parameters and annotations covering the safety profile, the only real gap is the missing routing guidance against the sibling create_claim_link.

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 imposes nothing the description must compensate for; baseline is 4. The description correctly focuses on outputs and lifecycle rather than inventing parameter detail.

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 concrete outcome: it returns a new API key plus a claim_url for account takeover and prepaid credits. That is a specific verb+resource pairing an agent can act on. It does not, however, distinguish itself from the sibling create_claim_link, even though it mentions a claim_url that overlaps conceptually with that 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?

'One key serves every later call' implies the tool is a one-time bootstrap step, which is useful implicit guidance on frequency. There is no explicit statement of when to use this versus create_claim_link or get_account, and no prerequisites or exclusions are given.

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=false, idempotentHint=false and destructiveHint=false, so the description's job is smaller. It does add genuinely useful behavior: the link is time-boxed to 30 days and grants account-claiming/credit-purchasing power. It omits whether calling again invalidates prior links and what authorization is required, which matters for a security-sensitive link generator.

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 with no filler, and the key facts (new URL, 30-day validity, purpose) are front-loaded. Nothing is wasted, though the brevity comes partly at the cost of the missing usage context.

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 shape needn't be explained, and the sole parameter is fully documented. Still missing for a link that grants account takeover: authorization requirements and the effect of repeated calls on existing links.

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 one optional parameter and schema description coverage is 100%, so the schema already explains api_key and the Authorization-header preference. The description adds nothing about it, which is acceptable at this coverage level but earns no bonus.

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 effect (returns a new claim_url) with the concrete outcome: a person can claim this account and buy credits. An agent can tell what it produces without opening the schema, though it never contrasts itself with the sibling create_api_key or get_account.

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 call this versus alternatives, no prerequisites (does the caller need an existing account/API key?), and no statement about whether it should be called once or repeatedly. The agent must infer all of that.

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 destructiveHint=false, so the safety profile is covered. The description adds the actual returned values (credits, claim state, check count), which is useful, but says nothing about authentication requirements or the api_key fallback behavior beyond what the schema states.

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 tight sentence that front-loads the primary return value (remaining credits) and packs three distinct outputs without 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?

An output schema exists so return-value structure is already documented, and annotations cover safety. The description is sufficient for an agent to call this correctly; the only minor gap is the absence of auth/permission 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?

With a single parameter and 100% schema description coverage, the schema fully documents the optional api_key. The description adds no parameter-level semantics, so the baseline of 3 is appropriate.

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 ('returns') plus the exact resource payload: remaining credits, claim status, and checks run. That field-level detail lets an agent distinguish it from siblings like check_receipt or create_claim_link, though it does not name those siblings 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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The agent must infer from the returned fields alone that this is the account-status lookup, which is implied rather than 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?

Annotations declare a non-read-only, non-destructive write. The description adds genuinely useful behavioral context beyond that: a human reads every report, no key is required, and an optional key links the report to the account. It doesn't cover reversibility or turnaround, but the auth and human-review disclosures are meaningful additions.

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 with the purpose front-loaded, followed by the trust and auth details. No filler; every clause carries 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?

With an output schema present, return values needn't be described, and annotations cover the write/destructive profile. The description supplies purpose, auth requirements, and human-review context, leaving only minor gaps like expected response timing.

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 75% and each property already carries a description, so the baseline is 3. The description adds value by clarifying brevity expectations ('a sentence or two') and the optional api_key's role, supplementing the enum and operation params documented 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 names a specific verb (report) plus the exact resource categories (missing capability, wrong result, bug), which map directly to the kind enum. An agent can tell instantly that this is a feedback-submission tool and distinguish it from siblings like check_receipt or get_account.

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 enumerated scenarios (missing capability, wrong result, bug) give clear context for when to use it, and 'in a sentence or two' hints at expected effort. However, no explicit when-not guidance or named alternatives are given.

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