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

Adds substantial context beyond the annotations: the write has no effect on any website or account, costs the user nothing, does not retry the run, and is the only path to a fix. It also describes the downstream flow where an account holder may be offered a live chat handled by `support`. One minor tension: annotations mark `readOnlyHint: false` while the text says 'it changes nothing' — the description clarifies that the only effect is a stored feedback record, so this reads as clarification rather than contradiction.

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?

Purpose is front-loaded and every substantive sentence carries novel information. The trigger enumeration is crammed into one long semicolon-chained sentence, which makes it dense to parse, but little could be cut without losing routing guidance.

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 two-parameter feedback tool with an output schema and annotations already present, this covers everything an agent needs: when to call, whether to ask the user, what to write, how to handle runId, and what to do on repeat failures. Return-value behavior is covered by the output schema.

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 baseline is 3, but the description adds real routing logic: include `runId` when reporting on a run, omit it when the gap came from `get_library`. It also constrains the free-text `report` payload to a sentence or two covering what was asked, what came back, and which site.

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 first sentence states a specific verb and resource: record what was missing, wrong, or incomplete about a Bowmark task so it can be built. It also implicitly separates this from `support` (a live chat escalation) and from `run`, which it references as the producer of the runId.

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 exhaustive trigger conditions — errors, timeouts, `partial`, empty results from a site that should have answered, untrustworthy data, and `get_library` gaps — plus the escalation path when the same task keeps failing. It also tells the agent to call it itself, in the same turn, without asking the user, which removes the main source of hesitation for an agent.

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