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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a pure read/analysis operation. It adds real value beyond the annotations: 'FREE' (no credit/quota cost), 'deterministic' (reproducible, not LLM-judged), the exact rule set checked, and the 0–100 score output. It omits whether it reports per-issue violations alongside the score, which would have made it a 5.

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 front-loaded sentence that puts the cost signal first and the output value last, with no filler. The parenthetical check list is dense but each item earns its place by scoping what 'limits' means.

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?

No output schema exists, so the description does explain the return value (0–100 Fit Score per platform), but not the result shape — whether violations, reasons, or per-check pass/fail are included, which an agent needs to decide whether to show results to a user. The undocumented 'hasMedia' param and the nested variants structure remain unresolved.

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 only 50%: 'variants' carries a shape hint in the schema, but 'hasMedia' is documented nowhere. The description never mentions either parameter, nor how media presence changes which checks apply (e.g., image/hook rules). With a coverage gap and a nested object param, the description needed to compensate and does not.

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?

Specific verb + resource: deterministically checks platform-specific post variants against verified limits and returns a 0–100 Fit Score per platform. The enumeration of checks (X weighted count, IG hashtag cap, Telegram caption limit, dead links, hook-below-fold) makes it clearly distinct from siblings like omnipost_publish or omnipost_platform_specs.

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 leading 'FREE.' signals a cost-based reason to prefer this call, and 'validate variants' implies a pre-publish check, but the description never states when to run it (before publishing?) or how it relates to alternatives such as omnipost_platform_specs, which likely exposes the same limits. Usage is inferred rather than stated.

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