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

Beyond readOnlyHint=true, the description adds real context: results are scoped to the signed-in user's own organization and an account is required. It stops short of disclosing whether chunks are truncated, paginated, or bounded in size, which matters for a document read.

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 short sentences with no filler; the core action and return content come first and the tenant scoping and auth note follow. Every clause carries information an agent would otherwise have to guess.

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 two-parameter read with full schema coverage, readOnlyHint, and no output schema, the definition is nearly sufficient: it covers scope, auth, and returned content. The remaining gap is volume/shape of the chunk payload, which the description leaves entirely implicit.

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 both orgId and documentId are documented, including which sibling tool supplies each ID. The description itself adds no parameter meaning beyond that, so the baseline of 3 applies.

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 and resource ("Read one evidence source document") plus what comes back ("its extracted text chunks"), which separates it from listing tools like list_evidence. It does not explicitly name a sibling alternative, so an agent must infer that list_evidence returns the index rather than the document body.

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?

Usage is only implied: you read a single document, and the schema parameter notes point back to list_evidence and list_organizations, which sketches the retrieval chain. There is no explicit when-to-use vs. search_evidence or read_proposal, and no stated preconditions beyond the account requirement.

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