the-fine-print

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral content beyond that: results are sorted longest-first and the comparison includes holiday extensions and fees, telling the agent what data will be present. It doesn't mention result size, pagination, or whether all retailers are always returned.

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 sentences with the substantive content (what is compared, sort order, included fields) front-loaded. The second sentence is mildly promotional ("no single shop's help page can") rather than informational, which is the only waste.

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 comparison tool with no output schema, the description covers the essentials: scope (all retailers), ordering, and the fields included (holiday extensions, fees). Missing only edge details like coverage breadth or result format, which are minor at this complexity.

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 is nothing for the description to disambiguate and the baseline of 4 applies. The schema coverage is 100% and additionalProperties is false, so there is no hidden input surface.

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 the specific resource (every retailer's return window) and the operation (put side by side, sorted longest first), which an agent can distinguish from get_policy (single policy) and list_companies. It stops short of naming the sibling tools explicitly, so differentiation is inferred from the cross-retailer comparison framing.

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?

"Answers questions no single shop's help page can" implies this is the cross-retailer comparison tool and that get_policy covers the single-shop case, but the routing is left implicit. There is no explicit when-to-use, when-not-to-use, or named alternative.

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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful provenance — answers are sourced from the company's own help page and stamped with the date checked — but says nothing about behavior when a company has no policy on file, coverage gaps, or error/lookup semantics.

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 sentence with no filler, but it opens with an example-list rather than the action, so the essential 'returns a company's policy' framing arrives late. 'Exceptions and catches' is also near-duplicative, costing a little density.

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 carries the burden of describing return content, and it does: components, source, and freshness are all named. Only the not-found / partial-coverage case is unaddressed, which keeps it short of full completeness for a single-parameter 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?

Schema coverage is 100% and the single 'company' parameter is documented with an example format ("Netflix", "best-buy"). The description adds no further meaning about accepted name/slug forms or lookup tolerance, so the schema does all the work — the expected baseline.

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 enumerates exactly what the tool returns for a single company: cancellation/return steps, deadlines, fees, exceptions, plus source and last-checked date. The 'one company' scope implied by the examples separates it from compare_return_windows and list_policy_changes, though the phrasing is a noun clause about return content rather than an explicit 'retrieves the policy for...' verb.

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 only implied: the agent can infer it should call this when it needs a concrete policy for one named company. There is no statement of when to prefer compare_return_windows (multi-company comparison) or list_policy_changes (recent updates), and no exclusions or prerequisites.

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=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the result (slug, kind, last-checked date) and asserting completeness via the word 'Every', which helps the agent reason about return values without an output schema.

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 front-loaded sentence that packs in the resource scope and the three returned fields with zero filler. Nothing is wasted or deferred.

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 listing tool with no output schema, the description covers the essentials by describing the returned fields, and 'Every' implies there is no pagination to worry about. Minor gaps remain: no statement of ordering or result-size expectations, and no hint of what an agent typically does next with the slugs.

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 is the baseline-4 case, and the schema is empty by design (additionalProperties: false). There is nothing further the description needs to document.

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 the exact resource (every company The Fine Print covers) and enumerates the fields returned: slug, kind (subscription or retailer), and last-checked date. It is clearly distinguishable from get_policy and list_policy_changes, though it never explicitly contrasts itself with 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?

The purpose implies a discovery/enumeration use case (e.g., to obtain slugs for get_policy), but the description never states when to call this versus the sibling tools or gives any prerequisite. Usage is inferred rather than directed.

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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that results are a chronological ('dated') log scoped to 'these companies', but says nothing about volume, pagination, or whether the log is complete or truncated.

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 that front-loads the key attribute ('dated log of changes') and spends no words on filler. Nothing could be removed without losing 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 no parameters and no output schema, the description carries more burden than usual and leaves the return shape underspecified — it does not say what a log entry contains (date, policy field, old/new value) or how large the result set may be. 'These companies' is also ambiguous about scope. Adequate but with clear 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 takes zero parameters, so there is no parameter semantics burden and the baseline of 4 applies. The description correctly implies the tool operates on the full set of companies with no filtering input.

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 resource precisely: a dated log of recorded changes to cancellation and return policies, which is clearly a historical/audit view rather than the current policy. It does not explicitly name how it differs from get_policy (current policy) or compare_return_windows, but the 'changes we have recorded' framing implicitly separates it from 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?

Usage is only implied: an agent can infer it should call this when it needs the history of policy revisions rather than the current policy text. There is no explicit when-to-use statement, no exclusion, and no mention of get_policy as the alternative for current values.

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