approve_application

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

With zero annotations, the description carries the full burden and does so substantively: it discloses that no submission is transmitted, that a dry-run receipt is recorded, and that non-Greenhouse sources return held=true/transmitted=false with a hold_reason. It omits permission/auth requirements beyond 'owner' and says nothing about idempotency or repeat-approval behavior.

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?

Three sentences, front-loaded with the action, then branching behavior, then the overarching caveat. Dense but each clause adds information; the final 'transmits NOTHING' slightly restates the dry-run point but earns its place as the key safety fact.

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 single-parameter mutation with no annotations and no output schema gets a fairly complete picture: what happens per source, the shape of the held response, and the no-transmission guarantee. Missing error/failure modes and permission requirements keep it from being fully complete.

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?

The single parameter has 0% schema description coverage, so the description must compensate. It implies application_id refers to a prepared application, but never states the expected format or whether it is a tracker/job-scoped identifier. Marginal help over the bare schema.

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 and resource ('Owner approves a prepared application') and branches by source (Greenhouse vs any other). It is distinguishable from siblings like prepare_application and reject_application by the 'approve' verb and the 'prepared' precondition, though it never names those siblings directly.

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?

'prepared application' establishes the prerequisite that prepare_application must run first, and the closing 'v0.1 transmits NOTHING' plus the APPROVED-AND-HELD path tells the agent what this tool does not accomplish. No explicit when-not-to-use or named alternative, however.

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