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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds two genuinely useful behavioral traits beyond that: results are ordered newest first and the listing is cursor-paginated, which affects how the agent loops for more. It stops short of stating default scoping behavior (holder defaults to "me"), what counts as a lease holder, or visibility/permission 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?

A single compact sentence with the scoping distinction and pagination facts front-loaded, no filler. It loses a point because the extreme terseness tips into ambiguity — the "(agents)"/"(humans)" parentheticals cost a few words while still leaving the scope unclear, so the economy is not fully earning its place.

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?

An output schema exists, so return values needn't be described, but the tool has four undocumented parameters at 0% schema coverage and the description explains at most two of them obliquely. For a filtered, paginated list tool, an agent still lacks the meaning of state and limit and the mechanics of following a cursor.

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 0%, so the description must carry parameter meaning and largely does not. "Your ... or anyone's" loosely maps to the holder parameter's "me" default, and "cursor-paginated" hints at the cursor parameter, but limit (default 50, max 200) and the state enum (active/released/expired/revoked) go entirely unexplained in both schema and prose.

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 parenthetical gloss "leases (agents)" identifies the resource, and "Your ... or anyone's" conveys the visibility scope, so an agent can tell this lists lease records rather than agents directly. However, the sentence has no explicit verb ("list" appears only in the name/title) and the "(humans)" contrast is cryptic without prior domain knowledge. It is recognizable but not sharply differentiated from siblings like list_agents or list_token_tree.

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?

There is no when-to-use guidance and no exclusions: nothing says to prefer list_agents for agent records, get_agent for a single agent, or release_lease when the goal is mutation rather than enumeration. The "your vs anyone's" hint implies a scoping choice but never ties it to the holder parameter or to any decision the agent faces.

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