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

Annotations already declare readOnlyHint, idempotentHint, and closed-world, and the description adds 'no key needed' auth context plus a rich account of what each row contains (driven vs only listed, agent level 0-5, stopping point, connection method, date, page). The 'not_covered' fallback for unknown names is genuinely useful behavior disclosure the schema never mentions.

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 sentences, zero filler, with the core action and constraint front-loaded and the return payload enumerated compactly afterward. The final 'Read-only, no key needed' short clause is terse despite overlapping 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 only two params, a full schema, and an output schema present, the description is more than sufficient — it even previews return fields and the not_covered edge case. The one gap is explicit routing against the closely named siblings choose_provider_for_task and get_provider.

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% and both parameters are documented there, so the baseline is 3. The description does echo the accepted identifier forms (slug, name, domain) and clarifies that task is optional background that adds a 'closest task' row, but that largely restates the 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 (Compare) and resource (products, 2-3) plus scope ('for one task, from our test drives'), which makes it distinguishable from single-product get_provider and decision-oriented choose_provider_for_task. The agent knows exactly what the tool returns by the end of the sentence.

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 implied rather than stated: sending 2-3 products signals batch comparison versus get_provider for one, and 'slugs (from search_tools)' routes the agent through the search sibling first. But there is no explicit when-to-use guidance against choose_provider_for_task or list_best_providers, and no stated exclusion for single-product lookups.

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