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

With no annotations, the description carries the full burden and does so: it discloses the blast radius ('nothing moves in the mailbox and nothing is archived'), the idempotent semantics, the concrete result values (unpinned / not_pinned), and the failure mode where a mismatched category yields not_pinned while the real pin survives. That last point is a non-obvious behavioral trap an agent could not infer from the schema.

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 action and its scope, then inputs, then return semantics — a sensible order with no filler. The clause 'read it, because a wrong category reaches that answer while the real pin is still there' is slightly convoluted but is the highest-value sentence in the description.

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 two-parameter tool with no annotations and no output schema, the description covers action, side effects, input sourcing, idempotency, and the shape and interpretation of the reply. Nothing an agent needs to call it correctly and interpret the result 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 baseline is 3, and the description adds real meaning on top: both values must be reproduced verbatim from list_feed output rather than reconstructed or guessed. It also warns that a wrong category silently produces a not_pinned answer, which changes how carefully the agent must source the enum 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?

States a specific verb and resource ('Remove a cluster's pin') and immediately scopes it against the mailbox-mutating siblings ('nothing moves in the mailbox and nothing is archived'), which separates it from archive_cluster and unarchive_cluster. The cluster-vs-conversation distinction is carried by 'cluster's pin' alongside the sibling unpin_conversation.

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?

Explicitly routes the agent to list_feed as the source of both inputs ('exactly as list_feed reported them') and clarifies the no-op case ('Unpinning something that is not pinned is not an error'). It does not state the inverse condition (when to use pin_cluster instead) or mention unpin_conversation as the alternative for single conversations.

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