Get an application

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world. The description adds real value: it clarifies that only local state is read and LinkedIn is never contacted (a stronger claim than readOnlyHint alone) and describes the shape of the returned state including answer provenance and needsInput flags.

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 [READ] safety marker, then two dense sentences that each carry useful detail with no filler or repetition.

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-parameter read tool with an output schema and full annotation coverage, the description is essentially complete; the only minor gap is any hint about the applicationId format/lookup, which the schema also leaves blank.

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 0% for the single applicationId parameter, so the schema does not document it. The name is largely self-explanatory and the description says nothing further about it, which is adequate but not compensating for the coverage gap.

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 (Returns/Get) and resource (local state of an in-progress application), then enumerates the returned content: status, CV, fields, questions with answer/source and needsInput. The phrase 'local state only, never touches LinkedIn' implicitly distinguishes it from siblings like linkedin_preview_application, though 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?

Usage is implied by 'in-progress application', which tells the agent the applicable context, but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as linkedin_preview_application or linkedin_provide_application_answer.

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