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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description correctly spends its words elsewhere: it discloses data handling ('analysed in memory and not stored') and, importantly, sets an expectation ceiling ('A clean result is not proof of safety'). It also names the shape of the result (file, line, rule, fix) with no output schema to lean on.

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?

Four short sentences, capability first, then return shape, then privacy, then the accuracy caveat. The rule enumeration is long but each item is decision-relevant for judging whether this tool covers a given concern; nothing is padding.

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 supplies the return fields, the data-retention behavior, the diff-scoping semantics, and an explicit false-negative warning. For a read-only analysis tool with two optional parameters, an agent has everything needed to call it and interpret the answer.

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 description coverage is 100% and already explains both modes, including that only added lines in a diff are checked and that path determines browser vs server classification. The description restates the two input modes but adds no syntax, size limits, or precedence rule when both are supplied, so baseline 3 applies.

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 ('Runs Claspine's Agent Shield rules on files or a unified diff') and then enumerates the concrete rule classes it detects (secrets, string-built SQL, unscoped tenant queries, log leaks, buffered uploads, platform-internal imports). Unmistakable against the doc-lookup siblings like api_reference, get_guide or search_docs.

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?

The two accepted input modes (files vs unified diff) make the intended call context clear, and the closing line routes the agent to a complementary check ('Spring Boot builds also run ProductBoundaryTest'). It stops short of an explicit use-this-when / not-this-when statement, so it is clear context rather than full routing.

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