send_batch

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

The description richly discloses behavioral traits beyond the annotations: it explains reuse semantics (returns recorded receipts, rejects differing plans), error handling, album splitting into groups of ten, reply_to and reply_part semantics, internal/provenance part handling, and signature metadata. This goes far beyond the basic readOnlyHint, idempotentHint, and destructiveHint flags and gives an agent a clear mental model of what happens.

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 description is dense but not wasteful; it packs multiple essential rules into a few sentences. It opens with the core action, then addresses idempotency, error handling, and part semantics in a logical order. It is appropriately sized for the complexity, though a reader must parse several compound sentences.

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 tool with 11 parameters and no output schema, the description covers many behavioral and edge-case aspects (idempotency, error handling, reply logic, album splitting). Yet it leaves some operational details vague, such as the exact format of 'recorded receipts' and how to interpret the returned state information, and a few parameters remain unexplained.

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 coverage, the description compensates for the most confusing parameters: request_id (idempotency, reuse), reply_to and reply_part (hierarchical reply relationships), and album parts (file count limit and splitting). However, it does not explain other parameters like agent, model, project, subject, route, contents, and template, which an agent may need to understand to call the tool correctly.

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 action (send) and the resource (an explicitly authorized batch) and situates it in a workflow (after draft review and structural preview). It implies the batch nature distinguishes it from single-send siblings like send_text and send_files, but it does not explicitly name those alternatives or contrast them.

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?

It provides strong operational guidance: how to use request_id (reuse for receipts, don't create a new id blindly), how to handle errors (stop and report confirmed state), and the requirement to inspect part states. It implies it should be used after preview_batch, but does not explicitly state when NOT to use it or compare with single-send tools.

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