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

Annotations provide readOnlyHint=true, and the description adds substantial behavioral context: it is deterministic, draws only from live installed manifests, returns grouped/tiered suggestions with default options flagged, and cannot suggest providers not installed. This goes beyond the annotation's safety signal and gives the agent a realistic model of the tool's behavior.

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?

The description is dense but every sentence serves a purpose: it states the core function, explains the mechanism, gives concrete examples, and distinguishes from a sibling. It is front-loaded with the primary action and maintains focus. Slightly long but not wasteful.

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 recommendation tool with no output schema, the description explains the output format (grouped, tiered, with default flagged), the input constraints (live manifests only), and the relationship to a sibling tool. It covers all the information an agent needs to invoke it correctly and interpret results.

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 both parameters are documented. The description enriches their semantics by explaining how each drives recommendations: 'description' drives email/sms/oauth/ai/payment triggers, and 'service_ids' drives most recommendations, with examples like ['cart','order']. This adds meaning beyond the schema's basic field descriptions.

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 verb ('RECOMMEND') and resource ('concrete provider integrations') and clearly differentiates from sibling build_list_capabilities by labeling itself as prescriptive versus descriptive. It gives concrete examples of what it returns, so an agent can unambiguously understand its purpose.

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?

Explicitly tells when to use this tool versus build_list_capabilities: 'call this so you don't OMIT a needed integration; use build_list_capabilities for a service's exact id + config fields.' Also provides usage context with examples like cart/checkout requiring a payment gateway.

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