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

Annotations already declare read-only, idempotent, non-destructive, but the description adds value they cannot: the observation is immutable, the payload includes a SHA-256 hash plus capturedAt and retention expiry, and — most usefully — it explicitly discloses what is NOT returned (no screenshots, media, or storage paths). Scope requirement and zero cost are also stated.

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?

Three tight sentences with no filler: identity/contents first, then requirements, then the negative return contract, then the sibling routing. Every clause carries information an agent needs.

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?

With no output schema, the description compensates by naming the returned fields and the excluded media types, plus the scope prerequisite and cost. Nothing material to invoking it correctly is missing.

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?

Only one parameter and schema coverage is 100%, with the schema itself explaining that the id is an evidence_id from investigation, evidence capture, or status observation. The description adds only the 'owned' qualifier and scope requirement, so the baseline 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 (Export) and resource (an owned immutable metadata observation), and immediately enumerates what it contains (SHA-256 hash, capturedAt, retention expiry). It is clearly distinguishable from the create-side sibling capture_evidence, which it names.

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?

Gives the prerequisite (requires evidence scope), a cost signal (free), and routes to the alternative for the opposite operation: 'Use capture_evidence with a quote to create a new observation.' It does not, however, contrast against the other read-style siblings (get_case, get_packet, get_operation), so the when-to-use-this-one framing is implied rather than stated.

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