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

Annotations already declare read-only, non-destructive behavior. The description adds value by disclosing stateful behavior ('current search'), pagination semantics, and that this endpoint is wired to the Job Cards widget rather than a general model-facing search. It does not claim any mutating side effects, so there is no contradiction.

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 two tight sentences with no filler. The essential action, pagination rule, widget context, and 'do not call' warning are all front-loaded and each 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?

For a tool explicitly marked 'Do not call from the model,' the routing guidance is complete, and the output schema plus annotations cover return/safety details. It still leaves some dependency on search_jobs for full filter semantics, but given the explicit non-model use case, this is a minor 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?

With only 15% schema description coverage and 20 parameters, the description cannot defer all meaning to the schema. It adds cursor semantics and says filters are 'same as search_jobs,' which is helpful, but the remaining filter parameters (e.g., workplace_type, salary_min, near_lat) still have no self-contained semantics in this definition.

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 opens with a specific action and resource: 'Fetch Job Cards for the current search,' and differentiates it by referencing search_jobs and cursor-based pagination ('Omit cursor for the first page; pass next_cursor to page'). It is immediately clear this is a paginated job-card retrieval tool, not the general search 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?

It explicitly tells the agent when not to use the tool: 'Do not call from the model,' and explains the first-page vs. subsequent-page behavior with cursor. 'Same filters as search_jobs' and 'Used by the Job Cards widget' provide context on how it fits alongside sibling tools.

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