update_config

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, so the bar is lower; the description nonetheless adds real behavioral context the annotations cannot carry — preference changes persist, tuning changes die at server restart unless `save` is true, `warn_on_missing_required_field` degrades errors into partial data, and a `domain` change may force re-authentication verified via check_session. It stops just short of describing the response payload, which is covered by the output schema.

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?

Front-loaded with the core action and dense with actionable detail, but it sprawls into a long run of clauses and offloads key enumeration to an external link rather than staying self-contained. Every sentence is largely load-bearing, so the penalty is mild.

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 3-parameter mutation tool with an output schema and full annotation coverage, the description supplies everything an agent needs: what may be changed autonomously, persistence semantics, the restart caveat, the partial-data side effect, and the required follow-up check after a domain change.

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, and the description earns an increment by explaining what specific key values mean (`domain` as the default site consumed by tools lacking `site`, `browser` as sign-in target) and by elaborating the `save` trade-off beyond the schema's one-liner. It does not enumerate the full key set, deferring to an external documentation URL instead.

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?

Starts with a specific verb+resource ('Change a setting') and immediately disambiguates the two classes of setting it mutates: user preferences (domain, browser) versus tuning knobs (request_timeout, thread_pool_size). It also ties itself to the sibling get_config by saying the key comes from there, so an agent can distinguish read-config from write-config without inspecting schemas.

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 explicit when-to-use rules for both modes: preferences 'only when the user asks', tuning settings autonomously 'when calls keep failing' with concrete trigger examples (timeouts, throttling). It also supplies an alternative path ('to read another site once, pass it as `site` instead') and guidance on when to offer `save`.

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