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

Annotations only declare this is a non-destructive write; the description adds the substantive behavior: org and user are derived from the sign-in (no auth params needed), a failed submit is non-blocking, and secrets/tokens/script_id must be excluded. That is context an agent could not recover from the schema or hints.

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 purpose, then guardrails, then the plug edge case, then body fields — a sensible order. It is dense and occasionally wordy ("with exactly what is needed and why") and contains a small wording slip ("Report a problem to viaSocket"), but no sentence 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?

For a 13-parameter, nested-object tool with no output schema, the description accounts for every body field including the optional ones and explains where identity comes from. The only gap is that it says nothing about what a successful submission returns, which is minor since no output schema is published.

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 baseline is 3, but the description adds the closed value sets for source and kind that the schema leaves as free strings with no enums, plus the required trio (source, kind, feedback). It further specifies refs.pluginId/refs.actionId for viaSocket-owned plugs and classifies a missing action/trigger/field as kind=missing_capability.

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 ("Report a problem to viaSocket") and enumerates the accepted problem classes (error, confusion, wrong docs/skills, user correction, missing capability), which sharply bounds what belongs here. It does not name the nearest sibling (report_published), so the agent must infer that the success/publish path lives elsewhere.

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 explicit when-to-use (problems only, never success), when-not (do not ask the user first), and failure semantics (a failed report never stops the task). It also routes a specific ambiguous case: a plug used in flows but absent from list_plugins is viaSocket's, so never edit it — report it here instead.

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