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

Annotations already cover safety (readOnly, idempotent) and open-world behavior. The description goes further by disclosing the data source, archival frequency (once per working day), 12-hour caching, keyless/free access, and coverage limits — operational facts annotations cannot express.

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 well-bounded sentences that front-load the core action, then layer source, use case, cost/latency, and coverage. Every sentence adds a fact an agent needs; slightly dense but 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?

For a simple 3-param read-only tool with no output schema, the description covers what it does, data provenance, freshness, limits, and cost. The only mild gap is that it doesn't describe the response shape (converted amount, rate), though annotations render that low-stakes.

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%; every parameter (amount, from, to) is fully documented with types, patterns, and examples. The description adds the currency-coverage caveat (unsupported codes like PKR, AED) which is genuinely useful beyond the schema, but does not clarify parameter syntax further. 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?

Specific verb+resource ('Convert an amount between currencies') with the data source named (ECB reference rates). It is clearly distinguishable from all siblings, none of which deal with currency, and the description preempts confusion by naming supported and unsupported currencies.

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?

Gives clear context ('Good for comparing fares quoted in different currencies') and an explicit negative boundary (currencies the ECB does not publish are unavailable). It does not name an alternative tool for unsupported currencies, but the exclusion is concrete enough to route the agent.

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?

Beyond the annotations (readOnly/openWorld/idempotent already cover the safety profile), the description adds genuinely useful operational context: 2 credits per uncached call and a 2-minute cache window. That pricing and caching detail is exactly the kind of behavioral trait annotations cannot express.

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?

Front-loaded with the purpose and returned fields, then a short usage note, then cost/caching. Every sentence carries information with minimal waste, though the field enumeration in parentheses is fairly dense.

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 helpfully lists returned fields; annotations cover the read-only safety profile; and cost plus cache lifetime complete the picture. The only missing piece is disambiguation from the single-flight sibling 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 description coverage is 100%, so the schema already documents airport_code, type, day, and limit. The description only echoes the type enum values, adding nothing beyond what the schema provides, which lands at the baseline for full coverage.

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 resource (upcoming departures/arrivals at an airport) and enumerates returned fields, so the agent knows exactly what data comes back. However, it never distinguishes this from the sibling get_flight_status, which an agent could plausibly confuse with a per-airport board versus a single-flight lookup.

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?

"Use type 'departures' or 'arrivals'" clarifies a parameter value, not when to choose this tool over siblings like get_flight_status or search_flight_prices. Usage context is implied by the resource name but no alternatives 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?

Annotations already establish read-only, idempotent, open-world behavior, but the description adds cost and freshness context the annotations cannot convey: 'FlightAPI key (1 credit per uncached call)' and 'results are cached for 2 minutes'. That is exactly the kind of operational detail an agent should know before calling.

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 tight sentences plus a concrete example, with the return payload front-loaded before the operational caveats. No filler or redundancy.

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?

There is no output schema, so the description compensates by naming the returned fields, and it also covers cost and cache TTL. Input constraints (date window, IATA pattern) live in the schema, so nothing an agent needs to call this 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 the schema already documents flight_number, date, and departure_airport formats and constraints. The description restates the two required inputs and supplies example values, but adds no semantics for departure_airport beyond what the schema already says. 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?

States a specific verb and resource ('Live status of a specific flight by flight number and date') and enumerates the response contents: scheduled/estimated/actual times, terminals, gates, baggage belt, departed/landed. This distinguishes it from get_airport_schedule (all flights at an airport) and search_flight_prices without requiring schema inspection.

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?

Gives a concrete invocation example and effectively scopes usage to a single flight identified by number+date, which separates it from the airport-wide sibling. It does not explicitly name alternatives like get_airport_schedule or state exclusions, so it falls just short of the when/when-not bar.

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 readOnlyHint=true and openWorldHint=false, so the safety profile is partly covered. The description adds genuinely new behavioral context: the counters are cumulative 'since it started' (explaining the non-idempotent, changing return values) and the call is free ('Uses no credits'), which the annotations do not convey.

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, front-loaded with the core purpose, followed by a short cost note. The longer first sentence is a necessary field enumeration because no output schema exists, so nothing 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?

With no output schema, the description correctly carries the burden of describing the return values and does so field by field, plus notes cost and limit semantics. Minor gaps remain (e.g., response format, whether counts are server-wide or per-key, when limits reset), but nothing essential for invocation 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema and description are consistent. Baseline 4 applies for a parameterless tool.

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 (Shows) and resource (this server's API usage), then enumerates exactly what is reported: call counts, cache hits, credits spent, and remaining per-minute/per-day limits. This clearly separates it from the sibling tools, all of which fetch external travel/currency data rather than server telemetry.

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 this is for checking quota/credit consumption before or after making calls, and 'Uses no credits' hints it is safe to poll. However, the description names no trigger condition and no alternative, so the when-to-use is left to inference.

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 cover the safety profile (readOnly, idempotent, closed-world), and the description adds non-obvious operational facts on top: it runs offline from a bundled OurAirports dataset, consumes no API credits, and ranks larger airports first. These materially affect how an agent budgets calls and interprets result ordering.

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 core capability and immediately followed by the routing guidance and the cost/ranking caveats. No sentence is filler; each adds distinct 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?

For a read-only lookup with a fully documented two-parameter schema, the description covers purpose, workflow position, cost model, and ordering. The only mild gap is the exact shape of a returned record (fields available per airport), which no output schema supplies, but the intended use case does not strictly require 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%, so the baseline is 3; the description goes slightly beyond by giving worked examples of query inputs and by explaining that results are size-ranked, which informs how the limit parameter should be set. It adds context rather than merely restating 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?

States a specific verb (Find) plus resource (airports) and enumerates the searchable keys (city, airport name, country, IATA/ICAO code) with concrete examples. An agent can immediately distinguish it from siblings like search_flight_prices or get_airport_schedule, which consume codes rather than resolve them.

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 'Use this first' and names the downstream tools (search_flight_prices, get_flight_status, get_airport_schedule) that require the IATA codes this tool produces. The when-to-use condition and the alternative-avoidance path are both spelled out, leaving nothing to inference.

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 readOnly/openWorld/idempotent, and the description adds substantive behavior beyond them: cost accounting (2 credits per uncached search), 30-minute caching semantics, indicative (non-bookable) prices, and that fulfillment happens off-platform. This is exactly the extra context an agent needs to decide whether to spend credits.

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?

Front-loads the core operation and mode distinction, then layers output shape, constraints, cost, and disclaimer. Four sentences, each carrying distinct information with no repetition of the schema.

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 takes on the return-value burden and does so explicitly (airline, total price, stops, duration, local departure/arrival times). Combined with cost, cache, and booking caveats, an agent has everything needed to call and interpret this 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 description coverage is 100%, so the schema already documents every parameter including defaults and formats. The description restates the IATA 3-letter constraint and return_date's one-way semantics, adding only marginal value over the schema, so the 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?

States a specific verb+resource (search live flight prices) and immediately defines the two operating modes with their differentiator (one-way vs. return_date round trip). It also names the sibling search_airports as the prerequisite when only a city is known, so an agent can place it precisely among the five 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?

Gives explicit usage context: one-way vs. round-trip driven by return_date, and a clear alternative/precondition for the IATA-code requirement (call search_airports first). The caching note (identical searches cached 30 min) further informs when re-calling is wasteful.

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