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

The description goes well beyond the destructiveHint annotation. It discloses the API request format ('wrapped as { data: {...} }'), required-by-API fields (path, body, photoUrl), the mechanism for linking to a profile via `fields`, and the return value. This adds significant behavioral context, including a warning about photoUrl being required by the API even though not required in the schema. No contradictions with annotations.

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 four sentences long, with the key 'MUTATES' flag front-loaded. Every sentence provides essential information: API endpoint, required fields, profile linking, and return behavior. There is no redundancy or filler, making it highly efficient.

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 create operation with no output schema, the description is remarkably complete. It covers the API endpoint, request body wrapping, required parameters, optional linking, and return value. It also clarifies the distinction between schema-required fields and API-required fields, which is crucial for correct invocation. The tool's complexity (nested `fields` object, profile linking) is well addressed.

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 schema already provides 100% coverage of all parameter descriptions, so the baseline is 3. However, the description adds meaning beyond the schema by explaining that path, body, and photoUrl are required by the API, that profileUuid should be passed through `fields`, and that `fields` merges extra fields. This helps the agent understand the API's expectations and the special role of the `fields` object.

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 clearly states the tool's purpose: 'publishes a post (a campaign/profile update)' via 'POST /posts'. This distinguishes it from sibling tools like create_donation, update_profile, or raisely_request, which target different resources or operations. The verb 'publishes' and the specific API endpoint make the action 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?

The description provides clear usage context: it is a mutating operation, and it explains how to link a profile via profileUuid through `fields` and how to pass extra fields. While it doesn't explicitly state 'use this instead of X' or list exclusions, the specificity of the POST /posts endpoint and the distinction from siblings like list_posts make the appropriate use case evident.

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