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

Annotations already declare destructive=true, idempotent=true and readOnly=false, but the description adds substantial independent context: requester gating, Ed25519 signing over a handoff-signed-req statement, the specific headers, the reference signer, and how to mint a key via `handoff enroll`. It also documents transport-specific signing behavior (single-use signatures on the SSE bridge, sign each message, sign the path without the sessionId). The one gap is that it never states what the destructive write actually replaces (existing hierarchy).

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 semantic model before auth and transport details, which is the right order. It is dense but nearly every clause is operational, with minor redundancy in the repeated signing emphasis ('SIGN as the requester' / 'AUTH — SIGN THE REQUEST') and a transport paragraph that is long relative to its weight.

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 destructive, auth-gated mutation with no output schema, the description covers the critical unknowns: who may call it, how to sign, and the meaning of the two semantic parameters. It stops short of stating overwrite semantics for an existing chain of command and gives no error or return behavior, but the essential call-time information is present.

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 only 33%: `orchestrators` and `request_id` are undocumented in the schema. The description compensates well for the ambiguous parameter, explaining that tiers are index-ordered top→bottom and that an agent may only order those in a LOWER tier, plus that orchestrators may order anyone at any time. Only `request_id` remains unexplained.

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 ('Set a project's chain of command') and goes further by defining the domain model: ordered tiers with index 0 at the top, ordering rights for lower-tier agents, and orchestrators who may order anyone. An agent understands the operation precisely, though no sibling (e.g. get_hierarchy, set_team_roster, set_project_leader) is named to anchor it in the family.

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 explains how to call the tool (requester-gated, sign as the requester) but never when to choose it over the many adjacent authority tools such as set_team_roster, update_permissions, set_project_leader, or set_goal_order. No exclusions or preconditions beyond the signing requirement are given.

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