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

Annotations already declare readOnlyHint/non-destructive, so safety is covered. The description adds real behavioral context beyond that: results are anonymous, individual votes are never attributed to a person, and it discloses the shape of the rendered chart and what aggregates are returned.

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 is front-loaded, followed by the return summary, then the routing rule to the sibling. Slightly dense across five sentences, but each sentence (including the example queries) carries distinct information and none is filler.

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?

Even though an output schema exists, the description adds the anonymity guarantee, the early-warning framing, and the sibling routing needed to call this correctly. Nothing an agent needs is missing for a single-parameter read 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 coverage is 100% and the single parameter's case-insensitive partial-match behavior is already documented in the schema. The description reinforces single-initiative scoping ('ONE initiative') but adds no syntax or format detail beyond what the schema provides, so baseline 3 is appropriate.

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?

States a specific verb+resource (get confidence signal and trend for ONE initiative) and explicitly contrasts with the sibling genchi_list_initiatives for the multi-initiative / beneath-initiative case. An agent can distinguish it without opening the schema.

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?

Explicitly says when to use it (single-initiative questions, with concrete example queries like 'is anything slipping') and when not to (work beneath an initiative, or spanning several), naming the alternative tool to use instead.

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