identity_login_oauth

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

Adds real context beyond annotations: deprecation status, the anonymous access policy, and that it is a delegating alias of an underlying controller method. Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) already signal a non-idempotent, external-facing write-like call, and the description does not contradict them. Token lifetime, response shape, and error behavior are unstated, which keeps it below 5.

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 notice is correctly front-loaded, but the text then carries markdown artifacts ("###", HTML entity ✔️) and repeats the endpoint path already present in the title and annotations. The access-policy table and alias sentence add little for an agent deciding whether to call a deprecated tool.

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?

The single most important fact for an agent – that this endpoint is deprecated and should be avoided – is present, and the body schema is fully self-documented. However, with no output schema there is no information about what a successful token response contains, and the deprecation has no effective date or replacement tool name, so an agent cannot fully judge whether calling it is acceptable.

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%: grant_type, code, refresh_token, client_id/client_secret, orgId, redirect_uri, scope and state are all documented in the schema, including the ignored-if-Authorization-header nuance. The description adds nothing about which parameters pair with which grant_type, so baseline 3 applies.

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 verb+resource ("Get Access token") and identifies the tool as an alias of the AuthenticationController's get access token method behind POST /csp/gateway/am/api/login/oauth. However, "Get Access token" is generic for an OAuth token-minting endpoint supporting multiple grant types, and the prompt for the replacement points at a raw API path rather than a sibling tool, so an agent still has to infer how this differs from identity_post_login, identity_get_access_token_with_refresh_token, identity_get_access_token_pkce_flow, etc.

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?

Explicitly marks itself [DEPRECATED] and states "Use this API instead: /oidc/oauth2/token" – a clear when-not-to-use signal that most definitions lack. It also discloses the access policy (Anonymous allowed), giving context on auth requirements. It loses a point because the recommended alternative is a REST path, not a sibling tool the agent can actually select, and it doesn't say when this tool is still the correct choice over the other identity_get_access_token_* siblings.

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