read_document

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

With no annotations, the description carries the full disclosure burden, and it does surface the key behavioral trait: a hard 50,000-character cap per call and the recommended workaround. It leaves out other behaviorally relevant facts — whether truncation is signaled in the response, what happens for an invalid doc_id, or whether the text is returned raw or as structured blocks — which matter for a read tool with no safety 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?

Two sentences, both load-bearing: the first defines the operation, the second defines the constraint and the preferred strategy. Front-loaded and free of restatement of the name.

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 three-parameter read tool with full schema coverage and no output schema, the description covers purpose, the size limit, and the recommended access pattern. The remaining gap is the response shape — whether the returned text is truncated silently and how the agent should detect it — which an agent would likely want before paging.

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 coverage is 100% and each parameter (doc_id, start_char, end_char) is already described in the schema, including the 50,000-character cap on end_char. The description reinforces the windowing concept but adds no format or edge-case detail beyond the schema (e.g., negative offsets, out-of-range clamping), so it sits at the 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?

The description states a specific verb and resource ("Read the text of a document") and immediately qualifies the scope with the optional character-window form, so an agent knows exactly what comes back. It does not name or contrast with the sibling readers (search_documents, list_documents), so differentiation relies on the schema and the doc_id hint rather than the description itself.

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?

It gives concrete usage context: for large documents, read the window around a known hit rather than paging through everything — a real strategy cue that steers the agent toward search-then-window instead of sequential paging. It stops short of naming the alternative tool or stating exclusions (e.g., when to prefer search_documents alone), so it is clear context without explicit routing.

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