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

Goes well beyond the readOnly/idempotent/openWorld annotations: discloses that the chain begins 2026-03-22, that hashes are computed once per UTC day close, that entries are append-only at the serving-role level, and the failure semantics of recomputation (a mismatch reveals silent edits). This is exactly the behavioral context annotations cannot carry.

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?

Labeled sections (Purpose/Triggers/When to call/Prerequisites/Next steps/Caveats) make it front-loaded and scannable, but the explicit field-by-field enumeration of full_data duplicates the existing output schema, and the trailing 'Output nature' sentence about past hit rates and sample sizes reads as template boilerplate that does not apply to a hash-chain integrity tool.

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 an audit/verification tool this is complete: chain inception date, computation cadence, immutability guarantees, the companion tool for recomputation, and the verification workflow are all stated. The output schema handles return-value structure, so 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% and the single 'days' parameter is documented in the schema with its max of 400. The description does not add syntax, default, or interpretation guidance for it beyond noting that each entry commits to all prior history. Baseline 3 applies when the schema does the work.

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: a daily SHA-256 hash chain providing tamper-evidence over prediction ledger rows, with the canonical recipe published for third-party recomputation. This is clearly distinct from sibling tools like get_resolved_predictions (raw rows) and get_prediction_accuracy (hit rates).

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?

Explicit triggers in multiple phrasings, a named ordering rule ('FIRST STEP of any serious credibility audit'), a periodic re-anchor rationale, an explicit alternative for raw rows (get_resolved_predictions), and stated prerequisites (none). When-to-use, when-else, and next steps are all covered.

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