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

The readOnlyHint=true annotation already declares the safe, non-destructive profile, so the bar is lower. The description adds only the API route (GET /v3/grants/{grant_id}/messages), which is mildly useful but discloses nothing about pagination behavior, result volume, or rate limits.

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 compact sentences with the core capability front-loaded before the API route. No filler, though the endpoint reference is of marginal value to an agent that already has the schema.

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 10-parameter read-only list tool, the definition is adequate: safety is covered by annotations and every parameter by the schema. It stops short of noting return shape or that page_token drives pagination, which would round it out since no output schema exists.

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 all 10 parameters (from, to, subject, unread, starred, page_token, etc.) are already documented in the schema. The description's "optional filters" adds no syntax or semantics beyond that, making the baseline 3 the correct call.

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 ("List") and resource ("email messages") scoped to the connected account, so an agent can distinguish it from the singular nylas_get_message. Differentiation from siblings is implied by "List" rather than made explicit, keeping it just short of a 5.

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?

"with optional filters" describes capability but gives no when-to-use guidance, no exclusions, and never names alternatives like nylas_get_message (single message) or nylas_list_drafts. The agent must infer the list-vs-fetch boundary from the tool name alone.

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