model_scores

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

With no annotations, the description carries the burden. It discloses the data composition (all council scores, avg, count, recent scores) but does not mention whether the data is live, cached, or whether there are any conditions (e.g., requires an active council). No side effects are implied, but for a read-only leaderboard this is adequate though not thorough.

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?

A single, readable sentence that packs essential information: the metric (leaderboard), source (council scores), and specific fields returned. No wasted words.

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 zero-parameter, simple aggregate query with an output schema, the description covers the behavior and contents. No additional context is necessary.

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?

The tool has zero parameters, so the description needs no parameter details. The schema coverage is 100% (vacuously). Per baseline guidance, 0 params earns a 4, and the description adds no unnecessary param info.

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 specific verb+resource: 'Per-model quality leaderboard' aggregated from council scores. It clearly identifies the output contents (avg_score, eval count, 5 most recent scores), distinguishing it from sibling council tools like council_reveal or council_score which likely operate per seat or per score.

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?

Implicitly clear that this is for viewing a leaderboard of model quality across all council scores. It gives no explicit exclusions or alternative tool references, but the context is sufficient for a simple query tool with no parameters.

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