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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), but the description adds real value beyond them: it discloses data provenance ('UNSIGNED expressions of interest'), a dependency failure mode ('GitHub may be unavailable'), and an interpretation caveat ('null counts do not mean zero'). That is exactly the kind of context annotations cannot express; it stops short of 5 only because it never says what fields the 'metadata' contains or whether results are paginated or cached.

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 short sentences, front-loaded with the data source and scope, followed by the trust caveat and the failure-mode caveat. Every clause earns its place, and the capitalised warnings are placed where an agent will read them before deciding to rely on the output.

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 zero-parameter, read-only tool with no output schema, the description covers provenance, trust level, and failure semantics well. The remaining gap is that it does not hint at what 'metadata' looks like (issue fields, counts, authors) even though no output schema exists to document the return shape.

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 tool takes zero parameters, so there is no parameter meaning for the description to add; the baseline for an empty schema is 4. Nothing in the description misdescribes inputs.

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 and resource ('Read metadata from ... public GitHub pilot issues') and immediately scopes it against the sibling categories: not identity-verified providers, funded buyer jobs, contracts, or paid services. An agent can distinguish this from siblings like browse_signed_offers or real_buyer_requests without opening any schema, even though those tools are not named individually.

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 word 'only' and the explicit exclusion list ('not identity-verified providers, funded buyer jobs, contracts, orders or paid services') give clear negative guidance about when this data is sufficient. Missing is a positive routing statement naming the alternative tool to use when the agent actually needs verified or contracted data, so selection between this and the many sibling browse_/real_ tools still requires inference.

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