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

Annotations indicate it is a mutation (readOnlyHint=false) but not destructive (destructiveHint=false). The description adds valuable behavioral details beyond that: the reference is 'credential-free' and 'expiring,' and it explicitly states 'no permission to other jobs, deletion or resharing.' It also notes the requirement for an explicit intended recipient, which is a precondition. This aligns with the annotations and adds context about side effects and constraints.

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 description is three sentences, front-loaded with the core action, then behavioral constraints. It avoids redundancy and every sentence adds information. It is slightly verbose in the third sentence ('Requires explicit intended recipient; no permission to other jobs, deletion or resharing') but remains focused and clear.

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 tool has 4 parameters, an output schema (not shown but indicated), and is a creation operation. The description covers the purpose, return type (reference), lifetime (expiring), and permission boundaries. It does not detail error handling or authentication prerequisites beyond the intended recipient, but the annotations and schema fill most gaps. Given the complexity, it is sufficiently complete for an agent to call it correctly.

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 75%, meaning most parameters already have descriptions in the schema. The tool description adds minimal parameter-specific guidance: it reinforces that recipient_client_id is the 'explicit intended recipient' but does not explain syntax, defaults, or relationships beyond what the schema provides. Since the schema already documents job_id, request_key, and ttl_seconds, the description adds little incremental value.

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 opens with a precise verb and resource: 'Authorize one recipient client_id to read one owned result with its own credential.' It clearly states the tool creates an expiring reference for agent handoff, and distinguishes it from siblings like get_result_reference (retrieval) and revoke_result_reference (revocation) by framing it as an authorization action. The scope is explicit: only one owned result, no permissions to other jobs, deletion, or resharing.

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 description gives clear context on when to use it: to grant a recipient access to a specific result via a credential-free reference. It mentions 'Owner access stays in the configured header,' implying this tool is only needed for non-owner recipients. It does not explicitly name alternative tools or say 'use X instead,' but the purpose is well-defined enough to guide selection against sibling names.

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