Product Recall for Agents

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

With no annotations, the description carries the full behavioral burden, and it falls short: it never says whether attestation is a write/irreversible action, what permissions are required, or whether the proof is validated. The only hint is that a 'proof of non-use' is involved, which is thin.

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?

It is a single short fragment with no wasted words, but it is under-specified rather than genuinely concise, and lacks anything like a complete sentence.

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 compliance/attestation tool with a nested object parameter, zero schema coverage, no annotations, and no output schema, the description is far too thin. An agent cannot determine required evidence, behavior, or return semantics.

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, but it only alludes to the 'proof' concept and says nothing about the structure of the nested proof object or what recall_id refers to. Both parameters remain effectively 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 pairs a specific verb (attest) with a resource (remedy), which distinguishes it from siblings like issue_recall or record_exposure. However, the domain jargon ('P97 omission certificate') and the fragment structure leave the operational meaning of 'attest remedy' vague to an agent without domain knowledge.

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 indication of when this tool should be used versus alternatives such as issue_recall, record_exposure, or completion. No prerequisites, sequencing, or exclusions are 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it says nothing. 'Attested' hints at a state change, but there is no mention of write semantics, required permissions, idempotency, or what the attestation does to the recall record.

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?

At six words it is short, but brevity here reflects under-specification rather than efficient conciseness; there is barely a complete sentence of information for an agent to act on.

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, no annotations, and 0% parameter coverage, the description needs to supply all context and supplies none. An agent lacks everything required to invoke this recall-completion tool 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 description coverage is 0% for the single recall_id parameter, and the description only obliquely implies it refers to 'a recall.' It adds no format, expected value, or meaning beyond the parameter name 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 phrase 'Attested completion for a recall' is a noun fragment that largely restates the tool name rather than stating a verb+resource action, so an agent cannot tell whether it marks a recall complete, verifies completion, or records an attestation. It offers no differentiation from siblings such as attest_remedy or record_exposure.

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 when-to-use, prerequisites, or alternative is given. The description never says under what circumstances completion should be invoked instead of issue_recall, attest_remedy, or record_exposure, leaving the agent to guess from the name alone.

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 the full behavioral burden, and it does disclose a genuine cost behavior: $0.01 per call with a first-call free allowance scoped to 'account AND wallet', plus an unexplained 'fleet covers'. However, it says nothing about whether the call is read-only, what data is returned, or any rate/scope limits beyond the free tier.

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?

It is very short and front-loaded, but the brevity comes at the cost of clarity: 'fleet covers' is cryptic jargon and the parenthetical mixes billing conditions without structure. It is compact but under-specified rather than efficiently 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?

With no parameters, no output schema, and no annotations, the description must explain what the tool returns and when to use it — and it does neither. A caller finishes this description knowing only the price, not the operation's semantics or result 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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to clarify about inputs, and the schema (empty object) is already self-consistent.

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 essentially restates the tool name ('exposure_query' → 'Exposure query') without stating what it actually returns or does. It adds a billing note but no verb+resource clarification, so an agent cannot distinguish it from record_exposure or the other siblings. This is closest to a tautology with pricing tacked on.

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 mention of alternatives such as record_exposure. The only usage-adjacent information is the pricing/free-tier note ('first free once per account AND wallet'), which hints at cost considerations but does not tell the agent when to invoke this tool versus a sibling.

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 the full behavioral burden, and it discloses only billing/cost behavior ($49 base, scaling above 100 exposed operators). It omits whether the recall is reversible, required permissions, whether it is destructive or state-changing, and what happens to related records.

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 compact sentence with the action verb front-loaded, so it is easy to scan. The parenthetical pricing detail is dense but not wasteful given it encodes cost 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?

For a mutation-style, three-parameter tool with no annotations and no output schema, this one-line description leaves critical information entirely absent: parameter meaning, authorization, reversibility, and 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 0% across three parameters (lot_id, reason, severity), and the description says nothing about any of them — no format for lot_id, no allowed severity values, no guidance for reason. The description fails to compensate for the total 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?

Contains a specific verb+resource ('Issue ... recall'), so the agent knows this creates a recall. However, 'signed severity-classed recall' is undefined jargon and there is no differentiation from siblings like attest_remedy or record_exposure, which are also action/recording 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?

No when-to-use, prerequisites, or alternatives are stated. The only contextual clause ('scaled above 100 exposed operators') describes cost scaling, not when the agent should pick this tool over its 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 behavioral disclosure burden. 'Operator-bound' implies an authorization constraint, but it does not describe side effects, reversibility, return behavior, or what exactly linking an output entails.

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 front-loaded sentence with no wasted words. The parenthetical is compact but slightly ambiguous, and no further structure is provided for a four-parameter 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?

Given four parameters, no annotations, no output schema, and 0% schema description coverage, the description is far too thin. It does not supply enough context for an agent to invoke the tool correctly or understand the meaning of its 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?

There are four parameters with 0% schema description coverage, and the description does not explain any of them. It generically mentions 'output' and 'exposed lot' but gives no meaning for kind, recipient, lot_id, or output_id, nor does it note that required parameters are zero.

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 ('Link') and resources ('output', 'exposed lot'), making the core action clear. However, it does not distinguish this tool from the sibling tools such as record_exposure or exposure_query, leaving the agent to infer the boundary.

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 parenthetical '(operator-bound)' hints at an operator-only context but gives no explicit when-to-use guidance, prerequisites, or alternatives. There is no indication of when this tool should be selected over siblings like record_exposure.

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 behavioral burden. It usefully discloses that records are deduped and hash-only, but it does not explain permissions, return behavior, or mutation 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 front-loaded phrase with no wasted language. It is concise, though its terseness contributes to gaps covered under other dimensions.

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 annotations, no output schema, and zero parameter description coverage, the description is too sparse. It gives purpose and two behavioral traits but omits parameter meanings and operational details needed for reliable 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% for three parameters. The description only alludes to the lot via 'to a lot' and does not explain agent or run_id, leaving most parameter meaning 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 states a specific verb and resource: 'Record load-time exposure to a lot.' It is clear what the tool does, but it does not explicitly distinguish itself from the sibling exposure_query 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 'load-time exposure' implies the usage context, but there is no explicit guidance on when to use this tool versus alternatives such as exposure_query. The guidance 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.