identity_check_id_token

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

Annotations already declare readOnly/ idempotent/ non-destructive/ openWorld, so the safety profile is covered. The description adds genuine value beyond that: error behavior on invalid or expired tokens, the overflow-claim expansion behavior, and an Anonymous access policy. However, it leaves the most operationally important detail unexplained — how the ID token is presented to a tool with no parameters (presumably an auth header, but that is never stated).

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?

Deprecation and purpose are correctly front-loaded, but the text has a real defect: the sentence 'This API has no analogue in Tenant Manager Display the content...' is missing punctuation and merges two unrelated statements. The markdown access-policy table and the repeated 'GET /oauth/check_id_token' also duplicate what the title annotation already provides.

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 parameters and no output schema, the description carries most of the burden, and it does describe the return content (claims, expanded group_names/group_ids) and failure mode. But the input mechanism for the token is absent entirely, which is a material omission for an agent trying to actually invoke this endpoint.

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?

There are zero parameters and 100% schema coverage, so the baseline is 4. Nothing in the description is needed to explain inputs, though a sentence clarifying that the token is implicit (from the session/auth context) would have resolved the obvious confusion.

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 and resource: display the content of the given ID token with expanded claims, erroring if invalid or expired. It also distinguishes itself from the validation use case and notes deprecation with no Tenant Manager analogue. The one gap is that it never explains how the token is supplied to a tool that declares zero parameters.

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?

It gives explicit when-to-use ('should be used to expand the overflow claims ... like group_names and group_ids') and when-not-to-use ('client validates an ID token locally instead'), plus a DEPRECATED marker. It stops short of naming any specific sibling as the alternative, because it claims none exists.

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