check_manifest

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

With no annotations, the description carries the full burden and does meaningful work: it states the source (lastseen.dev), defines handling for components not held ('reported as not_observed'), and explicitly frames the operation as lookup rather than advice. This is valuable behavioral disclosure beyond what the schema provides.

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 description is compact, front-loaded, and contains no waste. Every clause adds useful information: input format, output behavior, edge-case reporting, and the 'not advice' caveat. It is a model of concise tool documentation.

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, no-output-schema tool this is largely complete: it tells the agent what input to pass, how it will be interpreted, what results look like, and how missing components surface. It doesn't detail the exact response shape or rate limits, but no output schema exists and those are secondary for a simple lookup.

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?

The schema only says 'raw manifest text to parse', while the description enriches it by specifying the two accepted formats (GitHub Actions uses refs, or owner/repo lines) and the resulting interpretation per component. Since schema coverage is 100% but shallow, the description adds real semantic value.

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?

The description names a specific verb ('Parse'), the resource (a pasted manifest), and the return value (dated survival state per component). It also enumerates accepted input formats (GitHub Actions uses refs or owner/repo lines), distinguishing it from siblings like check_entity and check_org. 'Lookup, not advice' further clarifies its scope.

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?

It clearly indicates this tool is for parsing manifest-size input rather than a single entity or org, which aligns with the sibling context. It doesn't explicitly name alternatives or say when not to use it, but the input-type signal is strong and the closing 'Lookup, not advice' sets appropriate expectations.

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