apply_proposal

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the mutation side effect (writes to LinkedIn), the code-enforced approval format that must match exactly, the expectation of invalid-scope/permission errors until LinkedIn grants API access, and the instruction to report errors plainly without workarounds. This is exceptional transparency for a write operation.

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 three sentences, each dense with purpose. The critical differentiator is front-loaded, followed by the approval gating and error-handling context. There is zero filler; 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?

Despite no annotations, the description covers the full operational context: the single-write constraint, the mandatory human approval with exact argument format, the expected error condition and correct response (report and stop), and the relationship to propose_edit. With an output schema available to describe return values, nothing essential is missing for an agent to call 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?

Given schema description coverage is 0%, the description must fully explain parameter meaning. It does for 'approval' by specifying the exact string format ('approve <proposal_id>') and its role in the approval flow. For 'proposal_id', it links it to 'the single prepared request stored in one proposal', conveying its purpose, although it doesn't explicitly state where to obtain it (though imply it via propose_edit). This is sufficient value beyond the 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?

The description opens with 'THE ONLY TOOL THAT WRITES TO LINKEDIN', which immediately identifies the unique action (write) and resource (LinkedIn) while distinguishing it from every sibling. It then specifies it sends the single prepared request stored in one proposal, making the verb and object unambiguous.

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 states the precondition (human approval of the diff) and the prohibition against calling it on your own initiative or immediately after propose_edit without approval. This clearly delineates when to use it vs. alternatives like propose_edit, which creates the proposal that this tool then applies.

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