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

Adds genuinely non-obvious context beyond the annotations: the call is free (no credits), a brand profile is optional but sharpens output, and percentile values must be labeled as 'estimated'. It also enumerates the return payload's shape (pattern, strengths, fixes, rewrite, breakdown, percentile), which tells the agent what to do with the result.

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?

Front-loaded with the verb, scale and cost, then use cases, then prerequisites — a sensible order with no filler. The sentence enumerating return fields is somewhat redundant given an output schema exists, and the ragged line breaks add noise.

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 4-parameter scoring tool with an output schema, the description covers cost, prerequisites, trigger conditions, interpretation caveats and the effect of the save flag's domain context. An agent has everything needed to call it and explain the result correctly.

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%, so the schema already carries parameter definitions and the baseline would be 3. The description edges above baseline by explaining that the tool 'works without a brand profile, but is sharper with one', which gives implicit guidance on the optional audienceId parameter.

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 and resource ('Score one hook') plus the scale (0 to 100), and even defines what a hook is ('the opening line of a post or video'). The singular scope inherently separates it from the sibling hooks_generate, which produces hooks rather than rating one.

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?

Gives a concrete trigger ('when the user asks "is this hook good?"') and a proactive use case ('check a hook before generating content with it'), plus a prerequisite note that a brand profile is optional but improves results. It stops short of naming a sibling alternative or stating when not to use it, so it is clear but not fully exhaustive.

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