Scan a public repository

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lower, yet the description still adds real value: determinism with no LLM, a 2-90 s latency envelope, redacted secret evidence, and a description of the JSON report shape (summary counts, severity, file, line, advisory id, fixed versions). It does not state rate limits, repo-size ceilings, or failure behavior on unreachable/private URLs.

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?

Four tight sentences: action first, then scan coverage, then return format, then determinism and runtime. Nothing is repeated from the annotations and no sentence is filler.

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 one parameter, no output schema, and annotations covering the safety profile, the description supplies what's missing: return shape, runtime expectations, and determinism. Minor gap is that it never says how large a repo is too large or what happens on clone failure.

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 100% and the single `url` parameter is already documented with accepted hosts, so the schema does the heavy lifting. The description only adds the word "public," a marginal constraint beyond what the schema says. Baseline 3 is appropriate.

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 compound verb (clone + run feldspar-scan) against a specific resource (public git repository), and enumerates exactly what is checked: OSV advisories for lockfiles, secret patterns, config lint. The sibling (audit_pricing) is unrelated, so no differentiation is needed; an agent knows precisely what this does 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?

"Clone a public git repository" scopes when the tool applies (public, git-hosted, lockfile-bearing projects) and implicitly excludes private repos or non-git sources. It stops short of naming when-not conditions or alternatives, but there is no competing sibling for an agent to be routed away from.

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