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

Annotations already declare read-only/idempotent/non-destructive, and the description adds substantial behavior beyond them: statements are verified by reading each from its own transaction (bytes, hash), the statement chain, and a sample of loans against the pools' logs; the totals are Priors' claims checked only on that sample, up to the last statement. It also discloses a staleness/lossy caveat and that the response contains a rebuild command. That is exactly the kind of caveat an agent needs to interpret results correctly.

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?

Purpose is correctly front-loaded, but the remainder is a single dense paragraph with nested parentheticals ('the answer gives its block and date; later loans are not checked here') that is hard to parse on first read. Given there is no output schema, much of the length is justified, but the run-on phrasing and repeated 'the answer gives...' construction cost clarity.

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?

With no output schema, the description legitimately carries the return-shape burden and does so: it states what the totals represent, what the answer includes (last statement block and date, rebuild command), and the sampling caveat. It stops short of describing volume/pagination of loan records or the response's concrete structure, but nothing critical to calling 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?

There is only one parameter (agent_id), and schema coverage is 100% with the schema already giving format and an example ('e.g. 462'). The description adds no parameter-level semantics such as id ranges or lookup behavior. Baseline 3 is correct when the schema does all 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?

Opens with a specific verb+resource combination: 'Show the loan history Priors posted for an agent on the ERC-8004 reputation registry (Robinhood Chain).' The data source (erc8004-credit/v1 credit statements) and the entity (agent_id) clearly separate this from siblings such as agent_record, score_of, or pool_stats, so an agent can identify the tool without opening the 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?

Usage context is implied rather than stated: it tells you the history extends 'up to the last statement' and that later loans are unchecked, which scopes expectations. However, it never says when to prefer this over agent_record or score_of, nor names any prerequisite for calling it. Adequate but leaves routing to inference.

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