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

Annotations already declare readOnlyHint=true, so the safe-read profile is covered. The description adds the underlying v3 endpoint and the non-grant-scoped nature, but says nothing about pagination behavior, auth requirements, or result volume beyond what the schema implies.

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 short clauses, front-loaded with the core action and output meaning before the scoping note. The trailing "Nylas v3: GET /v3/grants" is mildly redundant but compact and useful for verification.

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 two-parameter read-only list tool with no output schema, the description supplies the key output fact (each entry carries a grant_id) and the scoping caveat. Only pagination/volume behavior is left implicit, which the limit/offset schema largely covers.

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% for both limit and offset, so the schema fully documents the parameters. The description adds no syntax, default, or range guidance beyond that, which is the expected baseline when the schema does the work.

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 (connected accounts/grants) and clarifies the output includes a grant_id used to scope other tools. This clearly separates it from the sibling nylas_get_grant, which fetches a single grant, so an agent can route without opening either schema.

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?

"Not grant-scoped" is an explicit condition telling the agent this tool does not need a grant_id, unlike most sibling tools. It does not name get_grant as the single-grant alternative, but the selection context is unambiguous.

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