identity_get_openid_configuration

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

Annotations already cover the read-only, idempotent, non-destructive, open-world profile, so the description only needs to add context — and it does: it discloses the deprecation/removal risk and an explicit access policy table showing Anonymous access, i.e. no auth required. It does not cover rate limits or response caching, so it is not exhaustive, but the two highest-value behavioral facts are 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?

The deprecation warning and replacement are correctly front-loaded, but the middle is filler: a generic explanatory paragraph about what OpenID Connect and OAuth 2.0 are contributes nothing to invocation. The markdown '###' headers and the repeated 'GET /.well-known/openid-configuration' line (already in the title/annotations) add structural noise for no decision value.

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 zero-parameter, read-only GET with full annotation coverage and no output schema, the description supplies the essentials: what it returns, the governing spec for the shape, auth policy, and deprecation status. The only gap is that the recommended replacement is not mapped to a callable tool, leaving the migration path slightly open-ended.

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?

The tool takes zero parameters and the schema is an empty closed object, so there is no parameter meaning to convey; baseline of 4 applies. The description correctly implies no input is needed by documenting only an HTTP GET against a fixed well-known path.

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 gives a specific verb and resource ('Get discovery endpoint meta data') and names the spec that defines the payload, so an agent knows exactly what is returned. It also flags the tool as legacy and names the successor path, which further pins down its identity. It stops short of 5 because it never relates the tool to any sibling in this otherwise huge identity_* namespace.

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?

The '[DEPRECATED]' prefix plus 'Use this API instead: /oidc/.well-known/openid-configuration' is an explicit when-not-to-use signal with a named alternative. What it lacks is a fully actionable route: the replacement is given as a raw URL path rather than as a tool the agent can actually call, so the agent is told to avoid this tool but not clearly what to invoke instead.

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