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

With no annotations at all, the description carries the burden well: it discloses determinism, no network, no LLM, and that the compromise check is against a static snapshot rather than live data. It doesn't state whether posted manifest content is persisted or how large an input can be before failing.

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 tightly packed sentences: purpose and inputs first, output shape second, boundary/exclusions third. Every clause carries information; nothing is repeated or padded.

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 3-param tool with no annotations and no output schema, the description supplies the missing behavioral context (what a finding contains, determinism, static data limits). It stops short of describing pagination or result ordering, which an agent might want.

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%, so the schema already documents filename, manifests, and upload_id including the either/or relationship. The description's 'POST ... or an upload_id' restates that relationship without adding format, size, or validation detail beyond the schema.

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+resource ('Dependency-manifest hygiene check') and then enumerates the exact input types and finding categories, so an agent knows precisely what comes back. It does not differentiate itself from the sibling supply_chain_scan, which is the closest functional neighbor.

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?

'NOT a live CVE feed - pair with npm audit / pip-audit / osv-scanner for that' is an explicit when-not plus named alternatives, and the two invocation modes (inline manifests vs upload_id) are called out. Missing only guidance against the in-house sibling (supply_chain_scan / coverage_check style tools).

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