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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds materially new facts: it is free, it does not re-fetch the target, and its return is tenant-scoped with no internal reasoning or other customers' data. These are cost and data-exposure disclosures the annotations do not carry.

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 dense sentences, front-loaded with what the tool reads, then cost/refetch behavior, then the alternative, then the return scope. No filler and nothing repeated from the schema or annotations.

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 characterizing the return (tenant-scoped case state, no internal reasoning or other customer data), and annotations cover the safety profile. One required parameter is fully documented, leaving no gap an agent would need to guess at.

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% and there is a single parameter, so the baseline is 3. The description only adds the ownership constraint (case owned by this organization) on top of the schema's note that id comes from investigate_url's completed operation.

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 (Read) and resource (stored observations/details for a case), and immediately scopes it (owned by this organization, does not fetch the target again). It distinguishes itself from investigate_url (which does the fetching) and from check_status, so an agent can select it without opening the schema.

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 an explicit routing rule: use check_status with a fresh status quote when a new content observation is needed, implying get_case is for re-reading existing observations. Covers the primary alternative but does not address other plausibly-overlapping siblings such as get_evidence.

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