get_secret

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses that the value is returned in a dedicated secret_value field and never embedded in prose, and it enumerates the three status outcomes (ok, missing, error) including the specific precondition behind error — no master key configured — plus a setup_hint field. What it does not cover is whether reads are audited or what access levels are required to read a secret.

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?

The first sentence front-loads the operation and its key constraint; the following sentences cover only return shape and failure modes. No sentence is filler — even the parenthetical about the value never appearing in descriptive text is a meaningful security guarantee rather than restatement.

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 single-parameter lookup tool, the description covers the input constraint, where the result appears, and every terminal status including the misconfiguration case. Because an output schema exists, the status enumeration is more than strictly required, and nothing an agent needs in order to call this 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?

Schema description coverage is 0%, so the description must compensate, and it does partially: "exact name" clarifies that matching is a literal name lookup rather than fuzzy or prefix matching, and the "missing" status ties that parameter to a concrete failure mode. It still does not describe naming conventions, case sensitivity, or scoping (project vs workspace), which the bare string schema leaves open.

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?

"Fetch a project secret by exact name" states a specific verb (fetch), a specific resource (project secret), and a scoping constraint (exact name) that separates it from a listing or search operation. It does not explicitly name siblings such as list_secrets or set_secret, so an agent must infer the boundary from the verb alone.

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 phrase "by exact name" implies this is the right call only when the caller already knows the precise secret name, suggesting list_secrets as the discovery path, but that is never stated. There is no explicit when-to-use, when-not-to-use, or named alternative, leaving routing to inference.

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