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

The description goes beyond the readOnlyHint annotation by explicitly stating 'Does not record a vote' and clarifying the internal Glicko-2 formula. It also explains the api_key requirement differences between public endpoint and /mcp/mcp, which is behavioral context an agent needs. No contradiction with annotations.

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?

Purpose in first sentence, then formula and workflow pairing, then auth note. No filler, each sentence carries distinct useful info.

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?

The description covers purpose, formula, workflow pairing, read-only behaviorhoed, and endpoint-specific auth. It doesn't mention output shape/return value, but the presence of an output schema partially mitigates that. For a prediction tool, the description covers the core decision context well.

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 0%; the tool description only explains api_key behavior. ranking_id, entity_a_id, and entity_b_id are not semantically defined beyond their names, leaving an agent to infer they refer to the ranking and two entities to compare. Since schema carries no descriptions stolen, this lack of elaboration leaves gaps.

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 states a clear action ('predict') and object ('matchup winner') with the specific timing condition 'before a vote.' It also distinguishes itself from vote-recording tools by explicitly saying 'Does not record a vote — read-only.' The sibling aimrank_submit_vote and aimrank_get_matchup are implicitly distinguished by this purpose.

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?

It clearly frames the tool as the prediction half of the 'Claude predicts, you vote, we compare' workflow and states the pairing with aimrank_submit_vote. It also gives endpoint-specific guidance about the api_key. It does not explicitly contrast itself with sibling prediction/retrieval tools like aimrank_get_matchup, but enough context is given for an agent to choose it for the intended flow.

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