Propose a Mira setup from a website

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond those: a latency expectation ('Takes up to a minute'), a scoping behavior ('Reads a sample of a website' rather than the whole site), and reinforcement that the output is a non-persisted draft. It does not contradict the annotations.

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 with zero filler: the first front-loads the core purpose and output composition, the second states the side-effect profile, the third states latency. The long component list earns its place because it tells the agent exactly what the draft will contain.

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 an output schema present, return-value details need not be restated. The description covers purpose, deliverable scope, side-effct profile, and latency. Minor gaps remain: failure behavior for unreachable websites and prerequisites are not mentioned, but these are edge cases for a tool whose schema and annotations already carry substantial context.

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%, so the baseline applies. The main description adds no parameter-specific meaning, but the schema itself is rich — especially useCase's 'Changes the brief it is designed against, not just its wording' and language's 'Restrict the pages read'. The description and schema together leave no parameter underspecified.

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?

The description states a specific multi-part action ('Read a sample of a website and propose a complete assistant setup') and enumerates the deliverable's components: persona, welcome message, grounded instructions, qualification questions, quick actions, privacy/imprint links, and a knowledge probe. This clearly differentiates it from siblings like crawl_company_website (crawls only), get_mira_settings (reads current config), and update_mira_settings (mutates config).

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 description gives clear context: this tool produces a settings draft for a website, and crucially states an exclusion — 'nothing is stored or configured' — which signals the agent this is not the tool for applying changes. However, it does not explicitly name alternatives (e.g., update_mira_settings for actually applying, crawl_company_website for just fetching pages), so the routing between siblings is left partly to inference.

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