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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so 'Read only' mostly restates structured data. The value-add is the domain-specific disclosure that no distribution is opened, no economics are hashed, and no money moves, plus the human-in-the-loop note ('A person still decides') — useful for a financial agent concerned about side effects, but it still omits what happens when a hash mismatches.

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 action and target, then trimmed to short exclusion clauses. 'A person still decides' is somewhat informal but conveys a real property (no autonomous decisioning), so it earns its place; the choppy fragments cost a little readability.

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 two-parameter read-only tool with no output schema, the description is adequate on inputs and safety but silent on the return shape — whether it yields a per-line pass/fail, a mismatch list, or an error when documents are missing. An agent cannot predict the result payload or failure modes from this text.

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% for both parameters, so the schema already carries the semantics of caseId and lineId. The description's phrase 'each reported funding line' loosely implies the optional lineId narrows scope to one line, but it never says so explicitly, so no real meaning is added beyond the schema.

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 (Verify) and a precise object (each reported funding line's documentSha256 against the file's documents), which is far more specific than the tautological title. It does not name a sibling tool it competes with, so an agent must infer the boundary with tools like read_package or walk_credit_file from the wording alone.

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 is only implied: the description establishes this is a narrow integrity check on reported lines within a case, and the exclusions ('does not open a distribution, hash economics, or move money') bound it negatively. There is no explicit statement of when to call this versus read_package or walk_credit_file, nor any prerequisite or sequencing guidance.

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