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

Annotations already declare readOnly/idempotent/closed-world, and the description still adds real substance: each input is returned with its reason and source, and 'missing inputs are listed, not guessed' — a meaningful honesty guarantee about what the agent can rely on. That is behavior beyond anything in the annotations or schema.

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 use case, then the return shape, then the parameter modes — a sensible order with no filler sentences. The long parenthetical enumerating score dimensions is dense but each item earns its place as scoring criteria.

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-optional-parameter read tool with no output schema, the description covers the return shape (score, per-input reason and source, missing-input list) and both invocation modes. Minor gaps remain: how many tools a category ranking returns and whether both params can be combined.

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% so the baseline is 3; the description adds the key semantic that 'tool' is optional and that omitting it ranks a whole category, plus gives example category values. It doesn't clarify precedence if both params are supplied, which keeps it at 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 and resource ('Check a tool ... Returns the Safety score') and enumerates the seven dimensions that make up that score, so the agent knows exactly what comes back. It also implicitly separates itself from siblings like get_tool/search_tools by framing the output as money-at-risk/Safety scoring rather than lookup.

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 a clear situational trigger ('before your agent connects to it') and covers the two modes: single tool vs. omitting tool to rank a category. It does not explicitly say when to prefer siblings such as compare_tools or get_incidents instead, so it falls short of a 5.

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