docx.text_find_locations

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

With no annotations, the description must fully disclose behavior. It states that all occurrences are returned (not just the first) and that coordinates are provided, which is useful. However, it does not explicitly state the operation is read-only (non-mutating) or describe the format of the returned coordinates (e.g., character offsets, line/paragraph numbers). For a find operation, these details are important for the agent to interpret results correctly.

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 a single, direct sentence that front-loads the action ('Find text and return exact coordinates') and provides a purpose clue ('LLM can see where to edit'). It is concise with no filler, earning a high score for structure and brevity.

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?

The tool is relatively simple (search and return locations), but the description leaves a notable gap: it does not specify the structure of the coordinates (e.g., character indices, element paths, or page numbers). This is critical for an agent to act on the result when editing. It also does not mention whether the search is case-insensitive by default (though the schema covers that). Given no output schema, the description should more carefully describe the return format to be fully contextual.

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 the schema already documents all three parameters (docId, searchText, caseSensitive). The description adds no extra semantic detail beyond hinting that the result includes coordinates. It does not clarify how caseSensitive interacts with the search or any edge cases. Given high schema coverage, a baseline of 3 is appropriate; the description does not compensate beyond that.

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 states a specific verb ('Find text'), resource ('text'), and outcome ('return exact coordinates of all occurrences'). It clearly distinguishes from siblings like docx.find (which likely just locates text) by emphasizing coordinates, and from editing tools like docx.replace_text. It also hints at its purpose ('LLM can see where to edit').

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 implies usage for editing-by-locating text ('LLM can see where to edit') but provides no explicit guidance on when to use this tool versus alternatives like docx.find or docx.replace_text. It does not mention exclusions or prerequisites. The usage context is suggestive rather than directive.

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