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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds valuable behavioral context beyond those flags: unknown ids land in a `missing` field, a near-miss suggestion is provided, and the remaining objects are still compared. It also explains that missing attributes appear as null in the matrix. This is meaningful behavior an agent could not infer from annotations or schema alone.

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?

The description is long but dense and well-organized. The core function is front-loaded, followed by when-to-use guidance, and then the edge-case behavior for missing ids. Every sentence contributes substantive information; the length is justified by the complexity of the comparison output. It could be slightly more concise, but it is not padded.

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 comparison tool taking 2–6 ids, the description covers the input contract, the full output shape, the intended question types, the prerequisite lookup workflow, and the failure mode for unknown ids. An output schema exists to handle formal return-value details, so the description need not list every field. The combination of annotations, schema, and description leaves no critical gap for an agent deciding to call this tool.

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%: the `ids` parameter is described as 'Two to six knowledge object ids, as returned by search, get_topic or get_related, in the order you want the columns.' The tool description only says 'pass the ids' and repeats the two-to-six range, adding no new meaning. Baseline 3 is appropriate because the schema carries the parameter semantics.

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?

The description names a specific verb ('Compare') and resource ('Football Atlas knowledge objects') and gives a detailed inventory of what is produced: cards, attribute matrices, shared tags, inter-object relations, common neighbours, and claims with sources and confidence. It is clearly distinct from get_entity (single entity) and search (find by name), so an agent can tell it apart from siblings without opening schemas.

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 description explicitly states when to use it: for questions like 'X vs Y', 'is X the same as Y', or 'how does X differ from Y'. It also gives a concrete prerequisite workflow: use search or get_topic first if you only have names, then pass the ids. It stops short of enumerating when-not-to-use alternatives such as get_entity or get_related, but the guidance is clear enough to route an agent correctly.

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