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

Annotations cover the safety profile (readOnly, non-destructive, openWorld), but the description adds real behavioral value: the API's ordering convention (newest page first), the required OAuth scope (job-applications:read), and notably what is deliberately NOT returned (phone, DOB, photo, files). That privacy boundary is the kind of trait an agent cannot infer from structured fields.

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 purpose and ordering, then the return fields, then the privacy caveat and routing advice. The mid-sentence field enumeration is slightly list-heavy, but it earns its place because there is no output schema to carry that 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?

With no output schema, the description compensates by enumerating returned fields and explicitly calling out the omissions, and it covers pagination, filtering, auth scope and sibling routing. Nothing an agent needs to invoke this correctly is missing.

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 100% and each parameter already carries its own doc string, including units, defaults, ranges and filter syntax. The description's mention of filtering by vacancy, stage or disqualified state only restates what the schema already defines, so baseline 3 is appropriate.

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 ('List job applications') and immediately distinguishes itself from the sibling read path by name-dropping homerun_get_application for single-record fetches. An agent can pick between the two without opening either 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?

Explicit routing ('ask for one application with homerun_get_application'), explicit filtering guidance ('filter by vacancy, stage name or disqualified state and page through') and an explicit exclusion ('do not use it to export all candidates'). When-to-use, alternative and anti-use are all present.

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