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

Annotations cover safety (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds non-obvious behavior beyond them: it executes immediately, returns the new wording, and — importantly — earlier measurements retain the old wording so pre/post-edit results are not comparable. It also discloses a validation failure mode. No contradiction with the 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?

Dense but front-loaded: the action, the precondition, and the return value come first, and the caveat and sibling routing follow. No sentence is filler — each one either sets the trigger, warns about comparability, or routes to an alternative.

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 3-parameter mutation with no output schema, the description covers what the tool does, when it fires, what it returns, what is preserved (historical measurements), and how to reach adjacent operations. Nothing an agent needs to call it correctly is missing.

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 100%, so baseline is 3; the description adds real value by stating the cross-parameter constraint that prompt_id must belong to the given project, plus the intent of 'text'. It does not add format/syntax detail beyond the schema, so it lands just above baseline.

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 ('Replace the wording of one tracked prompt') with concrete motivating examples (fix a typo, make it read like a buyer's question). It also distinguishes itself from the prepare_* siblings by stating it 'Runs at once', so an agent can tell it apart from the prepare/confirm flow.

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?

Gives the precondition ('after the user agrees'), the purpose of the edit, and explicit routing to alternatives: archiving goes to prepare_archive_prompts, adding goes to prepare_add_prompts. It also names a rejection condition (prompt_id not in this project), which is exactly the when-not guidance an agent needs.

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