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

Annotations already cover read-only, idempotent and non-destructive semantics, and the description adds substantial behavior beyond them: normalization of curly quotes, dashes, ligatures and line breaks; case-insensitivity by default; the warning that matches are extracted text rather than verified content; and the meaning of a zero-match result. This is exactly the extra context an agent needs before quoting a hit.

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-loads the core purpose in the first clause, then layers usage, filtering, normalization and caveats in order of importance. Sentences are dense but every one adds a distinct fact; nothing is restated from the schema or annotations.

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?

Even though an output schema exists, the description briefly outlines the return shape (total count, per-filing counts, page id, citation, snippet) and supplies the critical trust caveat that results are unverified extracted text. For a search-style tool with six parameters, nothing an agent needs to invoke 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?

With 0% schema description coverage the description must carry the load, and it explains `mode` (phrase/word/regex), `case_sensitive`, and `document` as a filename-substring filter. However, it never explains the `case` parameter, which is easily confused with `case_sensitive`, nor the `limit` parameter, leaving two of six parameters undocumented.

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 precise verb and resource ('Find every page whose extracted text contains...') and immediately scopes the mechanism to exact phrase, whole word, or regex. It is clearly distinguishable from the sibling `search`, which it explicitly characterizes as ranking by meaning.

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?

Names concrete use cases (quotation, dollar figure, cause or exhibit number, name, defined term) and names the alternative tool `search` along with the condition that selects it ('search ranks by meaning and may miss the exact words'). An agent can route between the two without opening either schema.

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