find_text

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

With no annotations, the description carries the full behavioral burden, and it delivers: it discloses that textbox matches are labeled separately, do not affect body indices, live mode returns the same flat-list shape, adds in_sdt entries, and caps at 500 matches with a truncated sentinel. This is unusually detailed and goes well beyond generic search-tool language.

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 core purpose is front-loaded in the first sentence, and the subsequent details about textboxes and live mode are all behaviorally relevant. The sentence structure is dense but not bloated; no filler or repeated schema information appears.

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?

An output schema exists, so detailed return-shape documentation is not required. The description covers search scope, result labeling, mode differences, and truncation behavior. The main gap is parameter semantics for regex and context_chars, but overall the description is sufficiently complete for a search tool with a clear schema and defaults.

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 0%, so the description must compensate. It explains include_textboxes thoroughly and describes the live-mode behavior, but it does not explain query, regex semantics, context_chars units/effect, or file_path handling. Two of six parameters are meaningfully annotated; the rest are left to inference from names and types.

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 opens with a specific action and resource: 'Find text in paragraphs and table cells; returns locations + context.' This clearly states the tool's function. It does not explicitly contrast with sibling search tools like find_formatted or search_and_replace, but the scope and output focus are concrete enough to avoid major 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?

The description gives clear context for when behavior changes: include_textboxes is 'file-mode only,' and documents open in Word are searched live with a different match set and a 500-match cap. It does not explicitly state when to prefer this over alternatives like search_and_replace, but the mode-specific guidance is actionable.

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