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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description still adds real behavioral context beyond them: it returns identity only, never document text or summaries, and it fails closed with result="no_source_pointer", a typed code, and safe_to_declare=false. That failure-mode disclosure is the valuable part; only the absence of any retry/rate-limit or error-recovery detail keeps it off a 5.

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?

Front-loaded with the core contract, then workflow, then output shape, then failure mode — a strong information order with no filler sentences. It is dense and slightly long with nested parentheticals, but every clause carries operational content.

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?

No output schema exists, so the description has to describe the return value itself, and it does: identity only (provider + resource id, with example formats and the supported provider list) plus the fail-closed shape. For a single-parameter read tool, nothing an agent needs to call it 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it must be the same pinned subject id that check_premises takes, and the tool never accepts a natural-language question. That constrains what a valid value looks like beyond the schema's minLength=1 string type.

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: returns the provider-native identity of the external resource backing a pinned subject's answer. It explicitly separates itself from siblings by naming check_premises and clarifying it 'never searches', so an agent can distinguish it from query_decision/verify_premises without opening schemas.

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?

Gives an explicit trigger ('after check_premises held you for a superseded source') and an ordered workflow: retrieve current answer, call this, then re-check and verify. It also gives a hard exclusion ('Never declare a source this tool did not return'), which is exactly the kind of when-not guidance that prevents misuse.

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