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

Annotations already establish readOnly/idempotent/non-destructive behavior. The description adds meaningful domain context: append-only sealing means counts drift from paper-published values, and it explains the record_versions resolution path. It does not describe return format or pagination, but this is contextual rather than behavioral.

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 two main outputs, but the second half is a long run-on sentence about record_versions and citation reconciliation. The content is useful but could be tightened or split.

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, so the description must convey what is returned, and it does: Brier score, counts, hashes, block heights, verification method. The append-only/record_versions explanation is a valuable completeness addition. Slightly verbose but covers the agent's needs.

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?

Zero parameters, so baseline is 4. Schema coverage is 100% and there is nothing to document; no parameter information is needed.

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 clear compound purpose: returns corpus calibration (Brier score, counts) and integrity proof (manifest hash, ledger hash, Bitcoin block heights, verification steps). Distinguishable from siblings like get_map or get_corpus_insights, though the sibling differentiation is only implicit.

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?

No explicit when-to-use guidance or alternatives. The mention of record_versions as a resolution path for stale citations implies usage context, but there is no comparison with sibling integrity or calibration tools.

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