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

Annotations only declare this is a non-read-only, non-destructive, closed-world write; the description adds the substance: pinning changes who can read the doc, can re-enable reuse of a private doc, auto-moves a task-chat doc into a space, and is actively refused in the privacy case. The refusal semantics plus the required human approval loop are exactly the kind of behavior an agent cannot infer from the annotations.

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?

Three sentences, each doing a distinct job: purpose, an edge case about a doc still in its task chat, then the refusal/consent path. Front-loaded with the verb and effect, with no filler. Slightly dense in the middle where the edge case interrupts the privacy explanation.

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 write with no output schema, the definition covers trigger, side effects, promotion of task-chat docs, and the refusal-and-retry path, which is what an agent needs to call it correctly. It leaves open what a successful call returns and what happens if the doc is already pinned, both minor here.

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 100%, so both parameters are already documented, and the schema's own text for share ("true only once your human agreed") carries most of the meaning. The description adds the sequencing around share - refusal, ask your human, call again - but nothing about doc_id state or format beyond what the schema says. Baseline 3 applies.

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 ("Pin a doc, presentation or storyboard to its space") and immediately explains the effect: every chat in the space and its sub-spaces reads it. The named content types and the concrete examples (brand rules, brief, source material) make the resource scope unambiguous and clearly separate it from the inverse sibling unpin.

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?

Explains when to reach for it (material the whole space must build on) and gives an explicit when-not: private docs are refused because a pin is team material, and the agent must ask its human before retrying with share: true. It also covers the precondition case of a doc still living in its task chat being promoted to the task's space first. It does not name unpin or share_link as alternatives, which keeps it short of a 5.

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