Get Applications

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description reinforces this by stating 'Read-only: it spends no credits.' It adds valuable behavioral context beyond the annotations: pagination details ('Returns 20 per page'), the strict definition of 'employer-confirmed', and what content is included for a single application. This fully discloses the tool's behavior and side effects.

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 information-dense but well organized: it leads with the core purpose, then use cases, confirmations, statuses, pagination, and a clear pointer to the sibling tool. There is slight redundancy where the 'Do not use it... use aiapplyd_review_application' instruction is repeated in the closing sentence, but overall 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?

For a tool with three parameters, rich annotations, and an output schema, the description is complete: it explains read behavior, credit implications, pagination, status meanings, and the exact distinction from aiapplyd_review_application. Nothing essential is missing for an agent to select and invoke this tool correctly.

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?

Input schema coverage is 100%, with all three parameters already described. The description adds meaningful context by explaining the status filter semantics, the pagination behavior tied to the page parameter, and that application_id reads one application in detail. It does not fully define every status value, but it compensates well beyond the baseline for schema-covered 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 description opens with a precise verb and resource: 'List the user's applications and where each one stands, or read one by application_id.' It also specifies what is returned for a single application, including the tailored resume, cover letter, screening answers, queue status, and employer confirmation image. It clearly distinguishes itself from the sibling action tool by stating it is not for acting on applications.

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 explicitly tells the agent when to use this tool: 'Use this to check progress, to find applications waiting for the user's approval... or to see whether an employer confirmed a submission.' It also provides an explicit exclusion: 'Do not use it to act on an application; use aiapplyd_review_application.' This is exemplary when-to-use versus when-not-to-use guidance.

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