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

Annotations already declare readOnly/idempotent/non-destructive, so the description is not needed for safety basics, but it adds meaningful disclosure: the exact return facets (capabilities, vault references with can_use/can_export, pending access requests, document locks, plan_readonly, next_steps) and the crucial 'Never returns secret values' guarantee. It stops short of noting whether results are scoped or how large the payload can get.

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, front-loaded with purpose and then the payload contents, with zero filler. The list of returned facets is dense but each item carries decision value for an agent.

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 no output schema, the description does the work of enumerating return values and the no-secrets guarantee, which is exactly what an agent needs for a read-only diagnostic. The remaining gap is the unexplained result_offset parameter and no mention of result set size or paging behavior.

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 0% for two parameters, and the description never explains either. project_id is inferable from the name, but result_offset is completely opaque — it is not stated whether it offsets the returned lists, and which lists, or how paging interacts with the returned collections.

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 ('Diagnose') and target ('whether this connector can work on a project'), plus the precondition context ('before a task that needs services or secrets'). This is clearly distinct from siblings like read_project, read_attention, or export_secret, so an agent can select it without opening the 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?

Gives an explicit temporal/contextual trigger ('before a task that needs services or secrets'), which is real when-to-use guidance. It does not explicitly name alternatives such as request_binding or request_access, but it hints at follow-up paths via 'next_steps for a missing binding or permission'.

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