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

With no annotations, the description carries the full burden, and it does disclose useful behavior: results are 'latest' records, 'source-backed', sorted fastest first, and labeled with collection status. However, it omits handling for missing data in some countries, auth/rate-limit requirements, and the shape of the 'collection status' label.

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 that front-loads the action and resource, with no filler. It packs sorting and labeling details efficiently, though the clause stacking makes it slightly harder to parse at a glance.

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 two-parameter tool with no annotations and no output schema, the description covers the result ordering and labeling but leaves service_key's format, error behavior, and partial-data handling unspecified. It is adequate but not fully self-sufficient.

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 only 50%: applicant_countries is documented as ISO alpha-2 codes with an example, but service_key has no schema description at all. The description says 'for one service' but never clarifies whether service_key is an ID, slug, or name, so it fails to compensate for the undocumented parameter.

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 (compare) and resource (latest source-backed processing-time records) with explicit scope (one service across several applicant countries). It is clear what the tool returns, though it does not explicitly name or contrast itself with the sibling get_latest_value, which likely covers the single-value case.

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 'across several applicant countries' implies the multi-country comparison scenario and distinguishes it implicitly from get_latest_value, but there is no explicit when-to-use/when-not statement or named alternative. The agent must infer the selection condition.

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?

With no annotations, the description carries the full burden, and it does disclose the shape of the payload (latest value, collection status, full history, forward-looking cohort estimates). However it says nothing about size/volume of 'full recorded history', pagination, or whether the read is safe/idempotent, so coverage of the behavioral profile is partial.

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: the core action and parameters first, then the return contents, with the conditional cohort-estimate clause clearly marked by 'Forward-looking IRCC routes also include'. 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?

There is no output schema and no annotations, so the description must carry return-value meaning, and it does describe the three main components plus a conditional fourth. Missing only operational detail such as response format or history volume limits.

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% for the single required parameter, so the description must compensate, and it does: the example 'ca-visitor-visa--in' reveals the expected entity_id format (route slug convention) that the bare 'type: string' schema omits. It stops short of documenting valid values or failure modes, but adds real meaning.

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 ('get one route by entity_id') and enumerates exactly what comes back: latest retained value, collection status, full recorded history, plus cohort estimates for forward-looking routes. This implicitly separates it from the sibling get_latest_value (history vs. latest only), but no sibling is named outright, so it falls short of the 5 bar.

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 guidance on when to reach for this tool versus search_entities, compare_values, or get_latest_value, and no preconditions or exclusions are stated. The agent must infer the routing decision entirely from the output-content wording.

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?

With no annotations, the description carries the full burden and does disclose non-obvious traits: 'latest retained' implies data may be stale, the source_collection_status precondition warns the value may not be current, and the NZ note pre-empts a surprising dual-record return. It omits auth/permission needs and error or empty-result behavior, so 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?

Three tight sentences with zero padding: the core purpose first, then the freshness caveat, then the NZ return-shape exception. Every sentence carries distinct, actionable 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 2-parameter getter with no output schema and no annotations, the description supplies the freshness caveat and a return-shape quirk, which are the two things an agent most needs. It does not describe the general shape of the returned record or what happens when no record exists, leaving a small gap.

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 their own descriptions (including examples for service_key and ISO format for applicant_country), so the schema does the heavy lifting. The description only restates that applicant_country is optional; it adds no syntax or format detail beyond the schema. 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: 'Get the latest retained official processing-time record for a service', with scope narrowed by the optional applicant country. It is clearly a single-record getter, which implicitly separates it from compare_values, but it never names or contrasts a sibling tool.

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?

Provides a concrete precondition ('Check source_collection_status before treating it as current') and explains that applicant_country is optional and what omitting it means (global metrics). It stops short of explicit when-to-use-vs-alternative routing against compare_values or search_entities.

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?

With no annotations, the description carries the full behavioral burden. It does disclose the return payload (matching entity_ids with latest source-backed values and collection status), which is genuinely useful since there is no output schema. However, it says nothing about pagination (limit default/max), ranking, permissions, or rate limits, leaving real gaps for a search endpoint.

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 tightly written sentences with no filler. The core action and scope are front-loaded, and the return summary follows immediately.

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 no annotations and no output schema, the description does the job of explaining what comes back (entity_ids, latest values, collection status), which is the critical missing piece. It stops short of covering pagination behavior or how to act on results, so it is strong but not exhaustive.

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 67%: query and jurisdiction are documented in the schema, limit is not. The description adds an example of free-text phrasing that the schema does not, which helps clarify query semantics (service and/or country terms), but it adds nothing about limit or jurisdiction scoping. Baseline 3 is appropriate given partial schema 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 names a specific verb (Search) and resource (tracked government processing-time routes) plus a concrete example query, so the purpose is unambiguous. It does not explicitly contrast itself with siblings like get_entity or compare_values, but the search-vs-retrieve distinction is inferable from the wording.

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 shows an example query format ('canada study permit pakistan'), which implies when the tool applies, but there is no explicit statement of when to use this versus get_entity, get_latest_value, or compare_values, and no exclusions or prerequisites. Usage 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.