get_excerpt

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

Annotations already mark the tool as read-only and non-destructive. The description adds meaningful behavior beyond that: it verifies that snapshot_id, document_id, and chunk_id are mutually associated before returning, and it emphasizes that the excerpt is bounded. This is useful context, though it does not describe what happens when verification fails.

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?

A single, front-loaded sentence with no filler. It states the primary action, the key scoping constraint, and the verification behavior in an efficient and well-ordered way.

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 simple read-only tool with schema-rich parameters, the description is nearly complete: the required ID set is justified by verification behavior, safety is covered by annotations, and max_chars is documented in the schema. However, there is no output schema and no explicit statement of the return format or error behavior when the association check fails, leaving a small gap.

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 high at 80%, so the baseline is 3. The description adds semantic value by explaining that the four required IDs are an association to verify, and the word 'bounded' hints at the effect of max_chars. This glue between parameters goes beyond the individual property descriptions.

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 precise action ('Return'), a specific resource ('one bounded evidence excerpt'), and adds the verification behavior that ties the ID parameters together. The singular 'one' also distinguishes it from the sibling get_multiple_excerpts, so an agent can tell the tools apart without opening their schemas.

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 this is the tool for retrieving a single bounded excerpt, which contrasts with get_multiple_excerpts, but it never explicitly names the alternative or states when-not-to-use this tool. Guidance is only implicit through the word 'one' and the tool name, leaving selection conditions weakly specified.

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