firefox_network

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

Goes beyond the annotations by disclosing the data scope, stating that cookies, headers, bodies and URL queries are omitted, which matters for privacy-sensitive consumers, and that collection requires persistent debug access. Annotations already flag destructiveHint=true and openWorldHint=true, and the description is consistent with them (clear/stop are the destructive operations). It does not describe the shape of what 'read' returns or whether start is per-tab or global.

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?

Three short, dense sentences with the core capability front-loaded, the prerequisite next, and the exclusion last. Nothing is wasted, though the first sentence packs four actions and three attribute names into one clause, which is dense but still readable.

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?

With 6 parameters, no output schema and 17% schema coverage, the definition leaves gaps: it never says what a 'read' returns (which fields per request), how the filters combine, what maxResults defaults to, or whether state is per-tab. It covers the prerequisites and privacy boundaries well, but not enough for an agent to predict results.

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 description coverage is only 17%, with only the resource-type parameter documented, so the description must compensate and it only partially does: 'duration, status and filters' loosely maps to statusMin, errorsOnly and maxResults, and the four action verbs map to the action enum. tabId, maxResults limits and errorsOnly semantics are left entirely to the bare schema.

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 specific verbs (start, read, clear, stop) against a specific resource (Firefox request metadata), and explicitly names the sibling firefox_performance as the alternative for resources not surfaced by webRequest. The phrase 'Firefox-visible request metadata' is slightly jargon-heavy, so it is not quite a perfect 5, but an agent can tell what this tool does and how it differs from neighbors.

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 an explicit alternative and the condition that selects it ('Use performance for resources not reported by webRequest') plus a prerequisite ('Collection needs persistent debug access'). It does not explain when to choose read versus clear versus stop, but those are implied by the verbs and the action enum.

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