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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real context beyond them: it explains that the 'verified' field is the server's own check while the evidence exists so the caller can repeat the verification independently, and it discloses the error behavior for ungraded dates. It stops short of describing latency or payload size, which keeps it at 4 rather than 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?

Three sentences, each earning its place: what is returned, how to interpret the verified field, and when to use this versus the sibling plus the error case. The most important scoping information is front-loaded and there is no repeated or filler text.

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?

An output schema exists, so return values need not be restated, and the description still summarizes the payload shape and the meaning of the 'verified' field. Combined with the sibling routing and the ungraded-date error case, an agent has everything needed to invoke this correctly for a one-parameter tool.

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 trading_date parameter is well documented with its YYYY-MM-DD format and a pointer to list_resolved_batches. The description adds meaning the schema does not: that an ungraded or unknown date is treated as an error, which tells the agent how to interpret a bad value. Baseline plus added error semantics justifies a 4.

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 (get) and resource (public proof for one graded book), then enumerates exactly what is returned: signed payload, hash, signature, content address, timestamp material, and verification steps. It also explicitly distinguishes itself from the sibling get_resolved_batch, so an agent can tell them apart without opening either schema.

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 explicit when-to-use guidance ('use this to check a book's signature and timestamp') and names the alternative with its purpose ('get_resolved_batch to read its forecasts and outcomes'). It also states a failure condition — an ungraded or unknown date is an error — which is the exclusion an agent most needs.

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