propose_edit

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

With no annotations provided, the description carries the full behavioral disclosure burden. It clearly states the tool does not write, builds a request, saves a proposal, and returns a diff. It also discloses localization handling for text fields. It does not mention idempotency or error cases, but the non-destructive nature is well communicated.

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 fairly long but every sentence adds value. It front-loads the core behavioral guarantee, then explains the parameter formats, and ends with locale localization details. There is no redundant fluff; it is compressed for the amount of information conveyed.

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?

An output schema exists, so return values need not be described in detail. The description covers the tool's purpose, parameters, workflow, and localization behavior, which is sufficient for an agent to call it correctly. Missing edge cases (e.g., invalid entity_id) are likely handled by the tool's error responses and the output schema.

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%, so the description must compensate. It provides detailed structure for the 'changes' parameter, distinguishing between simple text for headline/summary and action-based objects for position/skill/education. It also explains the locale wrapping behavior, adding significant semantic value beyond the bare schema. The other params (person_id, locale) are self-explanatory via defaults and names.

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 states a clear verb ('draft'), a specific resource ('profile change'), and explicitly distinguishes its behavior from the sibling apply_proposal by stating it 'NEVER writes to LinkedIn' and returns a diff for human review. This unambiguously differentiates it from the other proposal-related siblings.

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 instructs the agent to show the diff to the human, wait for approval, and only then call apply_proposal with the returned proposal_id. This gives both when-to-use and when-not-to-use guidance, clearly routing the agent to the correct sibling after this tool.

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