Request role

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

With no annotations supplied, the description carries the full burden and does so: it discloses that the outcome is policy-dependent (approval case vs immediate execution), that non-requestable roles are refused to avoid accidental grants, that the requester is always the authenticated user, that name/OID mismatches cause refusal, and that a write gate applies. That is exactly the behavioral context an agent needs for a mutation tool.

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?

Front-loaded with the core action and the policy caveat before any caveats about naming. The middle clause ("so by default this refuses roles ... because for those it would grant rather than request") is dense and takes a second read, and the trailing display-name sentence reads as a general convention rather than tool-specific instruction, costing a point.

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 an 8-parameter mutation tool with a nested fields object and no annotations, the description covers the decisive unknowns: policy-driven async approval versus immediate execution, the requestable-role restriction, identity of the requester, and the name-matching contract. An output schema exists, so return values need not be described.

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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: it explains that roleName/userName are midPoint unique names rather than display names, must match their OIDs, and that the call is refused on mismatch so the confirming human reads the right names. The display-name-over-OID convention for writes is also extra guidance not present in the schema.

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 and resource ("Request a role for yourself or a report") and immediately explains the underlying mechanics ("Submits an assignment-add delta; midPoint policy decides whether that opens an approval case or executes immediately"). It explicitly contrasts itself with the sibling assign_role, so an agent can separate the two without reading 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?

Gives an explicit when-not: by default it refuses roles the catalog does not flag requestable, with a named alternative for the deliberate-grant path (assign_role) and a pointer to list_requestable_roles for discovering valid targets. It also names the preconditions (write gate, authenticated user as requester) an agent must satisfy before calling.

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