Which Firefox profile is this?

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

Annotations only supply readOnlyHint=true; the description carries the real behavioral weight by disclosing the hard limitation that profile switching is impossible at runtime and by naming the environmental prerequisite (MOZ_REMOTE_ALLOW_SYSTEM_ACCESS) it reports on. It also implicitly enumerates the response contents, so the agent knows what evidence it will get back for verification.

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 sentences, front-loaded with the payload first, then the use case, then the immutability caveat and workaround. Every sentence adds decision-relevant information and nothing is repeated from the schema or annotations.

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 no output schema, the description fills the gap by naming the specific fields returned. Combined with the disclosed runtime constraint and the alternative approach, an agent has everything needed to decide whether to call it and how to interpret the result.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies no input is needed, staying consistent with the empty 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 a specific verb (report) and resource (the running Firefox profile), and enumerates exactly what is returned: ProfD, profile name, local cache dir, default-profile flag, and MOZ_REMOTE_ALLOW_SYSTEM_ACCESS status. This is clearly distinguishable from nearby siblings like browser_info and browser_page_info, which describe the browser/page rather than the profile identity.

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 use case ('confirm you are driving the browser you think you are') and an explicit non-use constraint ('the profile is chosen when Firefox STARTS; this server... cannot switch it'). It then supplies the concrete alternative workflow (launch a second Firefox with -profile <dir> and its own --remote-debugging-port, register a second MCP entry), so the agent knows both when to call this and what to do when it is the wrong tool.

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