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

With no annotations, the description carries the full burden and does so well: it discloses grounding behavior (cites attestation hashes), refusal semantics for ungroundable queries, a hard behavioral boundary (no recommendations/forecasts), the auth mechanism (x-api-key header or ?apikey=), and multi-turn session handling. This is unusually rich behavioral context for an unannotated tool.

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-loads the purpose, then behavior, then auth/session mechanics, then parameters. Every sentence carries information; the only mild inefficiency is restating parameters in prose the schema already names, though it adds limits not present in the schema.

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 2-param tool with no annotations, no output schema, and 0% schema coverage, the description covers purpose, behavioral boundaries, auth, session semantics, and param constraints. It could say more about what an 'envelope' contains or the shape of returned answers, but it is largely complete for correct invocation.

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 description coverage is 0%, so the description must compensate and largely does: it documents the 4000-char limit on query and explains session_id as the Session UUID from a previous envelope for multi-turn use. It adds real meaning the bare schema (just types) does not provide.

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: ask the Basis Agent a question about attested risk state. It is clearly distinguishable from data-retrieval siblings like basis_data or score_history by its Q&A framing. However, it never names an alternative tool or explicitly contrasts itself with the sibling set.

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 clear operating context: answers must be grounded in attestations, ungroundable queries are refused, and it never recommends positions or forecasts, which tells the agent when NOT to route forecasting/advice requests here. It stops short of naming which sibling to use instead for raw data retrieval.

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