recommend_improvements

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

No annotations are provided, so the description carries the full burden. It describes the output as 'concrete, deterministic recommendations' but does not mention any side effects, data mutation, authorization needs, or whether it is read-only. While likely non-destructive, this is not explicitly stated.

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 three sentences, front-loaded with key information. Each sentence serves a purpose: condition, output format, and role. No unnecessary 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?

Given the tool's complexity (6 parameters, nested object) and no output schema, the description adequately covers the output format. It lacks mention of error cases or prerequisites beyond being after score_initiative, but is sufficiently complete for its intended use.

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 83%, so baseline is 3. The description adds context by stating the output format (pillar-level targets with named actions and rationale) but does not elaborate on individual parameters beyond what is in the schema. It provides marginal value.

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 clearly states the tool's purpose: for initiatives classified Stop or Fix, it returns concrete recommendations to improve classification. It specifies the resource (initiative) and action (recommend improvements), and distinguishes from the sibling 'score_initiative' tool by positioning itself as the next step.

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 says to use after 'score_initiative' and only for initiatives classified Stop or Fix, providing clear context. However, it does not explicitly state when not to use (e.g., for Accelerate initiatives) or mention alternative sibling tools.

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