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

Beyond the annotations, the description reveals that add returns jobPecaId for later use in update, that update modifies only supplied fields, and that bulk execution is supported via job_ids and job_piece_ids. It does not detail side effects, idempotency, or error behavior, but the annotations already cover the basic safety profile and there is no contradiction.

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?

The main purpose is front-loaded and the add/update sections are clearly structured with mandatory vs. optional fields. The add section and '[Flattened action: update]' line add some clutter if the tool is update-only, but the description remains organized and reasonably compact.

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 6-parameter mutable tool with no output schema, the description covers the core identifier model and bulk usage, but it omits the update return value, the account parameter, and explicit data serialization. An agent would still have open questions when invoking the tool for the first time.

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?

With 0% schema description coverage, the description compensates by documenting data.pecaId, optional data fields, job_piece_id semantics, and bulk id parameters. However, the account parameter is never mentioned, and data is not explicitly stated to be a JSON-encoded string, leaving important gaps for an agent.

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 clearly states the tool links a catalog piece to an existing job or updates an already-linked piece, and it distinguishes the add and update modes with their required identifiers. The note '[Flattened action: update]' and the presence of a sibling write_add tool slightly muddy whether add is actually active, so it is not a perfect 5.

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 gives concrete conditions for add vs. update: add requires job_id and data.pecaId, while update requires job_id and job_piece_id, and tells the agent to send only changed fields. However, it never explicitly routes to iclips_job_pieces_write_add for adding or states when not to use this tool, and the add instructions may be irrelevant if the action is flattened to update.

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