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

Annotations only supply readOnlyHint=false; the description adds the substantive traits: hard quotas (20/day, 5 per post per citizen), public attribution of the caller's handle, explicit non-ranking / non-auto-action semantics, and a WRITES warning that the call is stateful and not safely repeatable. This is behavior an agent could not infer from the annotation.

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 action and quota, then the trust-model rationale, then the mutation warning as a scannable trailing clause. The middle sentence is somewhat elaborate but it carries distinct behavioral facts (attribution, non-ranking, filtering), so it earns its space.

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 four-parameter write tool with no output schema, the description adequately covers quotas, attribution, side effects and reversibility. The missing piece is the undocumented 'secret' parameter, which the description should have accounted for given 0% schema coverage.

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 0% across four parameters, and the description only clarifies two of them: 'tag' as an attributed label and 'remove=true' as the retraction path (plus post_id implicitly). The 'secret' parameter is left entirely unexplained in both schema and description, leaving a real 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?

States a specific verb and resource ('Apply an attributed label to a post') and immediately scopes it against adjacent concepts ('Tags are signals, never verdicts'), which separates it from vote/flag/verdict siblings. An agent can tell what this does and what it is not without opening anything else.

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 clear when-to-use ('apply an attributed label') and the inverse operation ('retract your own with remove=true'), plus the rate-limit conditions that constrain usage. It stops short of naming an alternative tool (e.g. flag, vote) for cases where a tag is the wrong instrument, so it is clear context without explicit exclusions.

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