Job Spotter

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real non-annotation context: ids are self-contained and stay valid later, and NHS Jobs / Teaching Vacancies results carry a closing date. It does not cover failure behavior for invalid or stale ids.

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?

Opens with purpose, then usage triggers, then the parameter rule, then provider caveats. Every sentence adds information and none repeat the schema verbatim.

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-param read tool with no output schema and full annotation coverage, the description supplies usage, parameter provenance and partial return-content hints (closing date). Remaining gap is what the response generally contains and what happens on an unknown id, which is 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?

Schema coverage is 100% and already documents the id format with examples, so the baseline is 3. The description earns above baseline by adding provenance and durability semantics ('pass the id exactly as given', 'ids carry what is needed, so they keep working later') that the schema does not state.

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 clearly that it returns details for a single job drawn from a search result, which cleanly separates it from the only sibling, search_jobs. An agent can tell this is the follow-up lookup tool 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?

Gives explicit when-to-use triggers with natural-language examples ("tell me more about the second one", "what's the apply link for the Uber job?"), and tells the agent exactly which value to pass and where it came from. The alternative (searching) is implicitly the sibling left for other cases.

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 cover the safety profile (readOnly, idempotent, non-destructive). The description adds non-obvious behavior: it parses level words, 'remote', 'in <city>' and 'this week' automatically, and it discloses an attribution obligation to Remotive/Himalayas/Jobicy/Remote OK that no structured field carries.

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 the what/where rule, followed by examples that earn their place by teaching query phrasing. Slightly example-heavy, but each one demonstrates a different parsing behavior.

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?

A read-only search tool with 6 fully documented params needs no output schema, and the description covers query formulation, natural-language extraction, and attribution. Only a brief note on result shape/limits per source is absent.

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 the baseline would be 3, but the description adds real semantics: which words to place in what vs where, and that natural phrasing like 'this week' or 'senior' is auto-extracted into the corresponding 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?

States a specific verb (Search) plus resource (current job listings), and the example queries make the scope concrete (query-driven listings search). It is naturally distinct from the single-item sibling get_job.

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 rich context on when and how to use it: quoted everyday phrasings ('find remote Python jobs', 'marketing jobs in New York') and the explicit what/where mapping. It doesn't name get_job as the alternative for fetching one listing's details, so it falls short of full routing guidance.

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