Evidence (reviews and professional tests)

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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers substantial extra behavior: independent per-side offsets advanced via next_offset while has_more is true, null-on-no-data semantics ('never means the model has no flaws'), a ~40 KB response cap with advice to lower limit, and text_truncated handling. This is well beyond what the annotations provide.

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 core purpose, then structured into pagination, null-semantics, and safety/size paragraphs. It is longer than typical but almost every sentence carries actionable information; only the untrusted-data warning is slightly redundant with common practice.

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 paginated, two-sided evidence tool with a rich output schema, the description covers return shape, pagination mechanics, edge cases (null vs empty), truncation, and size limits. An agent has everything needed to call it correctly and interpret results.

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, but the description adds real semantic value: it explains that both sides are returned each call and that buy_offset/not_buy_offset advance each side independently via next_offset, plus the truncation behavior tied to limit. This deepens understanding beyond the schema's per-field notes.

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+scope: 'Get published reasons to buy or not to buy a tire model.' It clearly separates this evidence tool from siblings like tires_list_tests and tires_get_test, which deal with professional tests rather than the buy/not-buy reason lists.

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 concrete precondition ('Check has_bnb_reasons on the tire card first to skip models without reasons') and explains the null-vs-empty distinction so the agent knows when this tool is meaningful. It stops short of naming an alternative sibling for the test-evidence use case, so it is clear context rather than full when/when-not routing.

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