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

Adds a lot beyond the annotations: all occurrences are replaced, case-sensitive literal-only matching, response includes an occurrence count plus read-after-write verification, and dry_run/expected_count act as safety gates. Most importantly it discloses that the call routes through Royally and blocks on human approval before anything changes — a critical trait the annotations do not convey. Slight deduction because it does not say whether the edit is reversible or what happens to revisions.

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?

Front-loaded with the core action before alternatives, semantics, guards, and the approval caveat — a sound ordering. It is dense and runs long in a single block, but essentially every sentence carries operational information.

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 destructive mutation with no output schema, the definition covers the important ground: what gets modified (post_content), how matches are counted, the human-approval gate, and the verification response. Missing only secondary details such as revision/undo behavior and error conditions.

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?

With schema coverage at 83%, the description still adds real meaning: it clarifies that find is literal/case-sensitive with no regex, that all matches are replaced, and that dry_run previews counts and expected_count aborts on mismatch. The one opaque parameter is `id`, which the schema leaves bare and the description only implies is the post ID.

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+resource ('find/replace a literal string inside a post's content') with scope ('any post type') and explicitly distinguishes itself from wp_update_post's full-content replacement. It does not differentiate against the near-identical siblings wp_replace_in_page or wp_replace_text_in_blocks, which is the main remaining ambiguity.

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 a clear use case ('surgical edits to large posts — page-builder content, embedded base64 payloads') and names the alternative it beats (wp_update_post). Also explains when to use dry_run and expected_count. It lacks explicit 'do not use when' exclusions against the block-level or page-level replace siblings.

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