Myrmigo

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

Annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=false, so the safety profile is covered. The description goes beyond that by describing the return payload (handler company, dated fees, deadlines, refund rules with sources, traveler's personal steps) and warns the rules vary by company/seller and change over time.

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 front-loaded with the 'Use this when...' trigger, then moves cleanly to outputs and caveats in four tight sentences. Every sentence carries information; it is slightly dense but not 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 no output schema, the description correctly carries the burden of explaining what is returned and the volatility of the data, and it scopes the covered booking types. For a read-only, fully schema-documented 3-parameter tool it is complete enough to invoke 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 100% and all three parameters (task, where, booked_via) are already documented in the schema. The description echoes some of this with 'including one bought via another site or agent' (booked_via) and 'which company handles it and where', but adds no new syntactic or format details, so baseline 3 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?

The description states a specific verb+resource (check change/cancel/refund rules for a booking) and enumerates the covered domains and booking types, so an agent can grasp the scope immediately. It does not explicitly differentiate itself from the sibling tools check_flight_compensation and find_official_booking_site, 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 gives strong triggering context ('Use this when a traveler asks how to change, cancel or get a refund...') with concrete examples and a timing cue ('Useful before opening the site'). It never states when NOT to use it or names the sibling alternatives, so no explicit exclusion 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 mark the tool readOnly, idempotent, and non-destructive, so the bar for added value is lower. The description exceeds it by disclosing that it stores nothing, submits nothing, relies on dated official sources, and is not legal advice — all meaningful behavioral context beyond the annotations.

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 front-loaded with the trigger condition and then packs in the output contents, limitations, data-handling guarantees, and claim route without wasted words. Every clause contributes useful routing or behavioral 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?

Despite having no output schema, the description spells out what the response contains: verdict, rule, amount, current airline obligations, facts that could change the outcome, claim path, and evidence. Combined with 100% schema coverage on inputs, an agent has 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?

Schema description coverage is 100%, so the schema already documents every parameter fully. The description reinforces some domain concepts, like overbooking and downgrades, but does not add significant semantic detail beyond what the input schema provides. Baseline 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?

States a specific action — checking EU261/UK261 compensation eligibility — and names the triggering events (cancelled, delayed, overbooked, downgraded). It clearly distinguishes the domain (flights only, not ferries) and gives a concrete sense of the result (verdict, rule, amount, claim path).

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 says when to use the tool: when a traveler's flight was disrupted and they ask what they are owed or their options. It also provides a clear exclusion ('Flights only, not ferries') and outlines the claim process, making the intended call context unambiguous.

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, destructiveHint=false, and the unusual openWorldHint=false. The description adds real value beyond these by enumerating what is returned (official site, booking page, own booking channels, dated rules with sources) and by disclosing a distinctive behavior: flagging sites not on the company's listed domains. It stops short of noting freshness/latency or what happens for unlisted companies.

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 sentences, front-loaded with the triggering condition, then returns, then exclusions — a sensible ordering. The middle sentence is dense (site, booking page, channels, dated rules, personal actions all in one breath) but 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 no output schema, the description must describe the return payload, and it does — enumerating official site, booking page, booking channels, dated rules with sources, and domain-mismatch flags. Combined with annotations carrying the safety profile, an agent has everything needed to select and call it.

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% and there is a single parameter, so the schema already fully documents 'where'. The description only implies the input via examples of company types and adds no syntax or format detail beyond the schema. Baseline 3 is the correct ceiling here.

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+resource: finding a named travel company's official site and booking page. It clearly delimits scope by saying it does not search fares/availability or book. Sibling differentiation is only implicit — the two siblings (change/cancel/refund, flight compensation) are never named, so an agent must infer the split.

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?

Opens with an explicit trigger condition ("Use this when a traveler asks how or where to book with a named airline, ferry, hotel...") and closes with explicit exclusions (fares, availability, booking). Both when-to-use and when-not are stated, leaving little to inference.

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