council_score

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

With no annotations, the description carries the full behavioral disclosure burden. It reveals that the server resolves hat->model itself, that scores feed a per-model leaderboard, and that scores are judged on correctness, depth, and actionability. It does not mention the response format or what happens on duplicate calls, but the core side effects are clearly disclosed.

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 dense and front-loaded with the purpose, followed by an example and scoring rubric. No filler words, but the embedded JSON example makes it longer than strictly necessary. Overall, each sentence contributes useful information.

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?

Given the lack of annotation and output schema, the description covers the essential workflow context: when to call, how to score, what fields to provide, and where results go (model_scores). Minor gaps exist: council_id is not explained and the return/acknowledgment behavior is unspecified. Still, the tool is well contextualized within its sibling workflow.

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 schema is minimal (0% coverage; scores items are free-form with additionalProperties), so the description must add meaning. It provides an example object shape with hat, score, and notes, defines the score range (1-10), and explains the scoring criteria. Council_id remains undocumented and notes optionality is unclear, but the description compensates substantially for the schema gap.

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 uses a specific verb-object pair ('Score each seat's reply') and immediately identifies the tool as the MANDATORY end step of every council. It distinguishes itself from siblings like council_reveal and model_scores by naming the exact temporal position in the workflow, so the agent knows exactly what this tool does and how it differs.

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?

Usage is explicitly stated: it must run AFTER synthesis and BEFORE council_reveal, and it is labeled MANDATORY for every council. The rationale (avoiding bias by model identity) provides context for why ordering matters. This is strong, actionable guidance for when to invoke the tool.

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