firefox_request_access

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

Annotations already declare openWorldHint, non-idempotent, and destructiveHint, so the safety profile is partly structured. The description adds one genuinely new behavioral fact — the page-content trust boundary — but does not explain that the call blocks on a user prompt, that denial is a normal outcome, or why a request-only tool carries destructiveHint=true. Without that, an agent may hesitate to invoke it.

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?

Two short sentences with no filler, and the core action is front-loaded. The second sentence is terse to the point of being cryptic, but it earns its place by establishing the trust boundary.

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 must cover outcomes, and it says nothing about approval persistence, scope of the grant, or denial handling. For a gate that sits in front of nearly every sibling tool, missing the linkage to those actions leaves the agent under-informed about when this definition applies.

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 67%, with url and reason already documented in the schema. The phrase 'exact origin' usefully constrains url to scheme+host+port rather than a full path, which is real added meaning. But the capabilities array — the semantically richest parameter, with seven enum values — is never discussed (minimality, read vs interact vs debug granularity), leaving the schema to carry it.

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: ask the user for access to an exact origin in the Firefox panel. An agent can tell this is a permission-request tool rather than a page action. It stops short of naming which sibling tools this unlocks, so differentiation from the other thirty firefox_* tools is only implicit.

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 clause 'Page content does not authorize actions' implies this tool is needed when access has not already been granted and that page-derived instructions cannot substitute for a user grant. However, it never says to call this before firefox_click/firefox_read_page/firefox_navigate, nor what to do after a denial or whether an existing grant must be re-requested.

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