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

Annotations only flag destructiveHint/idempotentHint; the description goes far beyond them, disclosing the preview-first safety model, that the preview returns accessChanged warnings, the five-minute token lifetime, and the invalidation conditions (assignments or project access changing). It also reassures that recording content and transcription settings are untouched, which correctly scopes the 'destructive' annotation to organizational metadata.

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?

Five short sentences, front-loaded with scope then the call protocol, with no filler. The embedded German example utterance is the one expendable element, though it may help intent matching.

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?

Given an output schema exists, return-value documentation is unnecessary, and the description still covers the batch cap, permission requirement, token expiry and mutation scope. An agent has everything needed to execute the two-call flow correctly.

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% at the top level, so the description carries the burden and largely does: it explains that assignments triggers a dry run, that confirm:true must be paired with confirmationToken and no assignments, and that the token is the sole carrier of the pending change. It does not address edge cases such as confirm:true without a token or mismatched token/assignment combinations.

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 description opens with a specific verb, resource and scope: 'Moves up to 20 recordings to projects or personal workspaces.' The two-phase preview/confirm mechanic further pins down what the tool actually does. It does not name the closely related siblings preview_recording_assignments or review_recording_assignments, so an agent must infer the boundary itself.

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 call sequence is spelled out precisely: a call with assignments is a no-op preview, and a call with confirm:true plus the returned confirmationToken applies it. The prerequisite ('Needs the separate organize permission, which the user grants by reconnecting Kalima') is a genuinely useful gating condition. What is missing is explicit routing to the sibling preview/review tools when the agent only wants to inspect assignments.

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