Ocolta Review Summaries

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

Annotations already establish readOnly, non-destructive, and closed-world behavior. The description goes beyond them with an explicit negative disclosure — it does not expose payment details or account identifiers — which is genuinely useful privacy/safety context for an agent deciding whether to call it. It stops short of describing idempotency or failure behavior when no purchase is connected.

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, zero filler, with the core identity of the resource front-loaded and the scope limitation following immediately. Every clause carries information the agent cannot get from the structured fields.

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 need not be spelled out, and annotations cover the safety profile; the description adds the resolution scope and the privacy boundary. The only real gap is the absence of guidance on choosing this tool over get_review_summary or list_recent_reviews.

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. The description correctly does not invent parameter semantics, and the implicit conversation-scoping is handled by context rather than an argument.

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 ('Identify') and resource ('existing Ocolta purchase connected for this conversation'), so the agent knows exactly what object is being resolved. It does not, however, name or distinguish itself from the siblings get_review_summary and list_recent_reviews, even though it mentions returning review counts — a point of potential confusion.

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 'for this conversation' implies a context-scoped lookup, but there is no explicit when-to-use statement, no exclusions, and no routing toward the sibling review tools that overlap in output (review count, report summaries). The agent must infer when this is preferable to calling those siblings directly.

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/openWorldHint=false, so safety is covered; the description goes further by disclosing data minimization (no source documents, personal fields, or free-text excerpts), the epistemic limits ('does not prove fraud, authenticity, intent, identity or AI generation'), and a cost trait ('No new credit is spent'). Error or failure behavior is still unstated, so not a full 5.

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?

Four compact sentences, front-loaded with what is returned before the caveats and cost note. One could argue the disclaimers are dense, but each conveys a distinct constraint rather than 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 values need not be re-explained, yet the description helpfully names the categorical fields anyway. Combined with the cost, privacy, and non-proof caveats, an agent has enough to call this correctly; only the meaning of the ID format is thinly 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?

Schema coverage is 0% and the single review_id parameter carries only a regex pattern with no prose. The description adds that the ID must denote 'one recoverable review from the connected purchase', which clarifies ownership/eligibility but not the expected ID form or what to do when a non-recoverable ID is passed.

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 (retrieve) plus the resource and even enumerates the payload: categorical status, priority, confidence, and fraud/AI indicator counts for one review. The scope phrase 'for one recoverable review from the connected purchase' separates it in spirit from list_recent_reviews, but no sibling is named explicitly, keeping it 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 line 'Provides signals for human follow-up' implies the use case but never states when to pick this over list_recent_reviews or get_connected_purchase, nor any prerequisite for obtaining a valid review_id. Usage is inferable, not prescribed.

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 establish readOnly/non-destructive/local scope, and the description adds genuinely new behavior: a cap of ten items, a 24-hour recovery window, and the reassurance that no new review or credit spend is started. The credit-spend note is valuable for an agent deciding whether calling has 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?

Three short sentences, front-loaded with the scope (up to ten recoverable reviews) before the usage condition and the no-cost guarantee. Every sentence carries information an agent needs.

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 need not be described. For a parameterless read tool, the description covers scope, result limit, time window, and absence of side effects — everything needed to call 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?

The tool takes zero parameters, so there are no argument semantics to explain; the baseline for a parameterless tool is 4. The description correctly implies the purchase context comes from the session rather than an argument.

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 (List) and resource (completed, recoverable Deep Reviews) scoped to the connected purchase, which lets an agent distinguish it from get_review_summary. It does not explicitly name a sibling alternative, 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?

It states a clear use condition: 'Use when you ask which review summaries are still available within the 24-hour recovery period.' That is concrete guidance, though it never names get_connected_purchase or get_review_summary as the alternatives for adjacent questions.

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