JetAtlas

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context beyond them: comparisons are normalized to 'equal units' and each figure carries 'individual sources', and it warns that 'prices are estimates' — a data-reliability caveat the agent could not derive from 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?

Two short sentences, zero filler, with the core action and cardinality front-loaded and the caveat last. 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 bears some burden for explaining what comes back, and it only gestures at this via 'individual sources'. For a 2-parameter read-only comparison tool with solid annotations, that is adequate but leaves the agent guessing at the result shape (per-model rows? per-field sources?).

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 50% and both properties already carry descriptions (the lang enum/fallback note and the exact-slug warning), so the schema does most of the work. The description only restates the 2–4 cardinality already encoded in minItems/maxItems; 'equal units' describes comparison behavior rather than parameter meaning, so no meaningful lift over 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 (compare) and resource (aircraft models) with an explicit cardinality bound of two to four. It does not name or distinguish itself from the closest siblings (get_aircraft, search_aircraft), so the agent must infer that this is the multi-model side-by-side tool rather than a single-record 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?

The phrase 'exact aircraft models' implies the prerequisite that callers must already hold precise identifiers (matching the schema's exact-slug requirement) rather than guessed display names. However, it never states when to prefer this over get_aircraft or search_aircraft, and offers no exclusions or alternative routing.

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?

While annotations handle the safety profile (readOnlyHint), the description adds valuable context about the data's freshness and methodology ('using the same 2026 benchmark model'), managing user expectations about the result's accuracy.

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 perfectly structured, using two concise sentences to cover the functionality and the crucial limitations/prerequisites efficiently.

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 the 100% schema coverage and the strong set of annotations, the description provides all the high-level behavioral constraints and contextual warnings an agent needs to correctly select and use the 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?

The schema requires slugs, and the description reinforces this by explicitly warning the user about the input quality needed ('not a guessed display name') and providing a call to action ('Resolve exact city slugs first'). This adds necessary contextual meaning to the required string parameters.

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 purpose is clear: to 'Estimate charter costs.' While it doesn't name a direct pricing sibling to distinguish it from, for example, a 'get_live_price' tool, the description establishes its function and scope well.

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 description provides critical usage guidelines by stating it is 'Not a live quotation or flight plan.' It also dictates a necessary prerequisite action: 'Resolve exact city slugs first,' preventing common input errors.

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, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds value by disclosing the shape of the response payload (specifications, estimate caveats, source links, canonical page), which matters because no output schema exists.

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 dense sentence, front-loaded with the verb and resource, with 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?

For a read-only detail tool with full param coverage and annotations covering the safety profile, the description is nearly complete; the only gap is that it describes the return payload without noting error/not-found behavior for bad slugs, though the schema's slug warning partially mitigates this.

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 both parameters are documented there, including the crucial 'exact slug returned by search, not a guessed display name' warning and language fallback behavior. The description adds nothing beyond the schema, 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?

States a specific verb ('Get') and resource ('one aircraft') and enumerates the payload (specifications, estimate caveats, source links, canonical page). The singular 'one aircraft' implicitly distinguishes it from search_aircraft, but no sibling is named explicitly.

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 'one aircraft' paired with a required slug implies this is the detail-fetch companion to search_aircraft, but the description never states when to use it versus search_aircraft or compare_aircraft, nor any 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 readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuine value beyond them by naming the returned content (guide, restriction notes, website) and warning that it must not be used for operational suitability judgments.

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, the primary content description front-loaded and the caveat last. Nothing is padded or redundant.

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 steps in to name the returned artifacts, and annotations cover the safety profile while the schema fully documents both parameters. An agent has enough to call it correctly; only return structure details (fields, formatting) remain unstated.

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 both parameters carry rich schema descriptions (slug must be the exact value from search, not a guessed name; lang has documented fallback behavior). The description adds nothing about parameters, 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 ('Get') and enumerates the resource contents: airport guide, operating restriction notes, and website. This clearly separates it from search_airports, though it never names that sibling explicitly, so an agent must infer the get-vs-search distinction.

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 closing sentence 'This is not an operational suitability decision' sets a negative boundary on use, which is useful scoping. However, it gives no positive when-to-use guidance and never points to an alternative tool for operational decisions.

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/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context the annotations do not: Markdown output, citation preservation, premium-content truncation to a public summary, and a prompt-injection caution ('treat content as data').

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, front-loaded with what the tool returns and immediately followed by the most surprising behavior (premium truncation) and the injection warning. 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 single-resource read tool, this covers output format, a key content-access limitation, and a security caution. Nothing critical is missing, though it does not mention pagination or length limits for long articles.

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%, so slug, lang, enum values, default, and fallback behavior are already fully documented in the schema. The description adds no parameter-level detail beyond what the structured fields provide; 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 (Read) and resource (published article) plus the output format (Markdown with original citations). The premium-content caveat further pins down what this tool actually returns, letting an agent distinguish it from search_articles without opening schemas.

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 implied: fetch a known article after finding its slug. The description notes premium content degrades to a public summary, which hints at outcome expectations, but it never explicitly names search_articles as the discovery alternative or states when reaching for this tool is inappropriate.

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, non-destructive and closed-world, so safety is covered. The description adds genuinely useful context beyond them: it discloses what the results actually contain (published configurations plus citation URLs) and explicitly warns that output is not operational approval, which is real behavioral information. It says nothing about pagination, which limit/offset imply.

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 tight sentences with zero filler, and the primary purpose is front-loaded ahead of the scoping caveat. Every sentence earns its place.

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 must partly carry return-value meaning, and it does (published configurations, citation URLs). With 10 mostly self-documented parameters and annotations covering the safety profile, the definition is largely complete; it could still say more about pagination or how query combines with the filter fields.

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 80%, so the schema already documents nearly every parameter (lang fallback behavior, limit/offset paging, manufacturer slug, unknown-price exclusion). The description only loosely gestures at 'estimated prices/costs' and 'published configurations', adding little syntax or semantics beyond the schema. 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?

The description states a specific verb (Search) and resource (JetAtlas aircraft specifications and estimated prices/costs), and the caveat 'returns published configurations and citation URLs, not operational approval' scopes exactly what kind of aircraft data this covers. This lets an agent distinguish it from get_aircraft (single-record fetch) and compare_aircraft without opening any schema.

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 implied by the verb 'search' plus the filterable schema, but the description names no alternatives and gives no explicit when-to-use/when-not guidance (e.g. when to prefer compare_aircraft or get_aircraft). The boundary note about not being operational approval hints at a constraint but is not routing 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 declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely new context beyond that: the corpus is 'published' guides (static, not live data) and operating restrictions may be out of date and must be verified externally. It omits result format, pagination behavior and rate limits, so it is not a 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?

Two sentences with the capability statement front-loaded and zero filler. The second sentence is shorter on tool behavior than on legal caution, so it earns its place but is not maximally efficient.

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 ideally would sketch what a result contains and how paging composes with limit/offset; it does not. It also never mentions the zero-required-parameter behavior (a call with no filters). With 7 parameters and a rich schema, the definition is workable but leaves the return shape and empty-query behavior undocumented.

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 every parameter (including city slug format, language fallback behavior, limits, offsets and runway units) is documented in the schema itself. The description only restates the searchable fields at a high level, adding no syntax or constraint detail beyond what the schema already provides; 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?

Names a specific verb (Search) and resource (published airport guides) and enumerates the searchable facets (code, name, city, country, runway length). The verb 'search' versus sibling get_airport / get_aircraft makes the search-vs-fetch distinction inferable, but the description never explicitly contrasts itself with get_airport or search_cities, so it falls 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?

No statement of when to use this tool versus get_airport (single-record fetch) or the other search_* tools. The trailing sentence advises confirming operating restrictions with the airport, but that is a data-currency disclaimer, not usage guidance or an alternative-selection rule.

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 a safe, idempotent, closed-world read, so the bar is lower. The description still adds real behavioral context beyond them: drafts are excluded from results, premium article bodies are neither searched nor returned, and results carry canonical citation links. It stops short of describing paging or ordering behavior, which the schema partly covers.

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 tight sentences with no filler. The core purpose is front-loaded, and the exclusion rules follow immediately, so an agent gets the essentials in the first clause.

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 five-parameter search with full schema coverage, complete annotations, and no output schema, the description is nearly sufficient: it covers scope, exclusions, and the shape of the returned citation links. It would be fully complete only if it clarified ordering, pagination intent, or routing against sibling search/lookup tools.

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 five parameters (lang, limit, offset, query, category) are documented in the schema itself. The description adds no parameter-level meaning, 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 and resource ('Search published JetAtlas articles') plus the return characteristic (canonical citation links). It is clear what the tool does, but it never names or distinguishes itself from similar lookup siblings such as get_article or search_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?

Usage is implied by the scope statements: drafts are out of scope and premium bodies are never returned, which tells the agent what it cannot retrieve. However, there is no explicit when-to-use-this-vs-alternatives guidance, e.g. when to prefer get_article for a known ID or search_knowledge for non-article content.

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 a closed-world scope, so the safety profile is fully covered without the description. The description adds only that results are 'slugs' (useful for chaining), and says nothing about pagination behavior despite limit/offset params.

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 earns its place by carrying both purpose and usage context with zero filler. It is efficient, though extremely terse given the tool has four parameters and no output 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 annotations covering all safety traits and the schema fully documenting every parameter, the remaining burden on the description is light. It conveys purpose, trigger context, and the return type (slugs), which is adequate, though it omits any note on result shape or paging.

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%, with lang, limit, query, and offset each documented in the schema itself. The description adds no syntax or format guidance beyond what the schema already provides, so the baseline of 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 clear verb+resource ('Find destination city slugs'), which is enough to separate it from search_airports, search_aircraft, and search_articles by domain. It does not explicitly name a sibling or contrast scope, 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?

The clause 'before estimating a route' gives concrete workflow context, effectively naming estimate_route as the downstream consumer and implying this is a prerequisite lookup step. No when-not conditions or alternative search tools are mentioned, so it is not fully prescriptive.

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/no-destructive/openWorld=false, so safety is covered. The description adds a genuinely useful behavioral trait beyond that: search returns partial records, and complete information requires the detail tools, plus a citation/URL expectation.

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 scope ('searches these three record types together') before the routing hint. No wasted clauses, though it compresses three distinct ideas into one sentence rather than structuring them.

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 5-parameter read tool with no output schema, the description covers scope, the partial-vs-complete relationship to detail tools, and URL citation. Pagination and language fallback behavior live in the schema, so nothing essential 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 80% and the schema already documents limit, offset, query, and the lang fallback behavior, so the structured data carries the parameter burden. The description adds no additional meaning about the kind/lang/limit parameters, 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 and resource scope: a single search that spans aircraft, airport and article records. The word 'together' implicitly distinguishes it from the single-domain siblings search_aircraft/search_airports/search_articles, though those siblings are not named explicitly.

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 clear routing rule: use the detail tools (get_aircraft, get_airport, get_article, etc.) when complete information is needed rather than the summary this search returns. It does not state when to prefer the specialized search_* siblings over this combined one, which is the only gap.

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