Issue Authority Delegation

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

Annotations only declare the write/no-idempotent profile; the description adds substantial context beyond them: the record lives in this process's in-memory revocation store and is lost on restart, authorization is solely possession of the server key, remote invocation is refused, and the return is a signed JSON record the caller must retain. That is exactly the behavior an agent needs before committing to a mutation.

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?

Dense but front-loaded: identity and record type first, then alternatives, then spend policy, then the operational caveats. Nearly every sentence carries decision-relevant information, though the server-key/issuer sentence and the persistence warning could perhaps be tightened.

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 11 parameters, no output schema, and a mutation annotation profile, the description covers what the structured fields cannot: return shape (signed JSON the caller keeps), durability limits of the revocation store, and the authorization/deployment preconditions. Nothing essential to a correct invocation is missing.

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. The description earns above baseline by explaining the spend policy as bounded-by-default and naming the three spend fields versus spend_unbounded, plus the aps-hierarchical-v1 grant syntax. It adds framing but does not touch depth_remaining, values_required, or the ceilings, which the schema already documents.

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 artifact: issuing a signed root AuthorityDelegationV1 with record type and spec section. It explicitly distinguishes itself from create_delegation (legacy, non-revocable under SDK 8) and names revoke_delegation and check_authority_delegation as the lifecycle partners, so an agent can place it precisely among siblings.

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 the condition that selects this tool over the legacy alternative ('Legacy create_delegation records cannot be revoked under SDK 8') and names the tools that consume the output. It also states an explicit exclusion: the tool is refused on a remote server (MCP_TRANSPORT=sse or MCP_REMOTE=1).

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