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

The annotations already flag destructiveHint: true, but the description goes far beyond by explaining the exact effects: leaves public surfaces (article page, directory, search, creator feed), stops being payable, and importantly, there is no undelete tool. It also notes idempotency (deleting an already deleted piece returns success, only missing or non-owned ids 404), and that the return is a 204 with no body. This is extremely transparent about every behavioral nuance.

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 compact yet comprehensive. Each sentence adds critical information: soft-delete behavior, irreversibility, alternative tool, idempotency, error cases, return format, and authentication instructions. No superfluous words or redundancy.

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?

Given the destructive nature and lack of output schema, the description covers everything an agent needs: the full effect of the operation, all edge cases (re-deletion, missing id), the authentication requirement, and the alternative tool. It leaves no gaps for a high-stakes mutation tool with two parameters.

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 coverage is 100%, meaning both parameters (postId and signInWithX) are already described in the schema. The description adds significant value beyond the schema: for signInWithX it clarifies it must be fresh, single-use, and references the recipe from publish_essay; for postId it mentions the id comes from publish_essay or list_my_posts. This assists the agent in constructing correct inputs.

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 'Soft-delete one of your pieces by id', which pairs a specific verb ('delete') with a resource ('piece'). It also distinguishes this from the sibling tool 'update_essay' by explicitly noting that setting status to 'draft' is reversible whereas delete is not, making the purpose unmistakable.

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 explicitly tells when to use this tool (when you want a piece removed from all public surfaces and stop being payable) and when not to use it (if you only want it off the market temporarily, use update_essay to set status to 'draft' instead). It also mentions that there is no undelete tool, so the agent knows the alternative is irreversible.

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