Write a Firefox preference

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

Annotations already flag this as non-read-only and destructive, but the description earns credit by adding traits annotations can't express: the change outlives the session, some prefs are locked, and some are only read at startup so the write is deferred until restart. It still doesn't say what happens when a pref is locked (silent failure vs. error) or whether success is reported.

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 tight sentences with the privileged-context caveat front-loaded, then persistence, then the restart caveat. Every sentence carries a non-obvious fact; 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?

For a destructive, persistent config mutation with no output schema, the description covers the two biggest agent risks: durability and deferred effect. The residual gap is failure semantics for locked prefs and whether the tool returns confirmation, but the definition is largely sufficient to call it responsibly.

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 100%, including the enum for 'type' and the per-type value encoding, so the schema carries full parameter burden. The description adds nothing about the name/type/value triplet beyond what the schema states, which is the expected baseline here.

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 ('Set a preference'), and the '(privileged context)' qualifier makes clear this is a low-level browser config write, not a page-level action. It doesn't name the obvious siblings browser_get_pref, browser_search_prefs, or browser_reset_pref, so differentiation must be inferred from the verb alone.

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?

Usage is only implied by the verb: an agent can guess this is the write counterpart to browser_get_pref and browser_search_prefs. No sentence tells the agent when to prefer browser_reset_pref over setting a value, or what prerequisites (privileged context) must be satisfied before calling.

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