notification_document_add

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

Annotations are all false, so the description carries the burden. It discloses key behavioral traits: this tool only registers metadata, not the file bytes, and should be used before activating. It also reveals the two-step sequence (register then get upload URL). However, it does not discuss error handling, whether registrations are additive, or idempotency behavior (consistent with the false idempotentHint).

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 concise sentences, each with a distinct purpose: first defines the operation, second states when to use it, third clarifies what it does not do and directs to the complementary tool. No redundancy or filler.

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 the tool's moderate complexity, the description covers the what, when, and sequencing. The output schema likely covers return values (not shown). It lacks explicit mention that the request must be in draft state, though 'before activating' suggests it. Overall, an agent can correctly select and invoke the tool with this description.

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 50% (only requestId has a description). The description adds meaning by specifying that requestId comes from notification_request_create and identifies the hash as SHA-256. It also frames attachments as 'fileName + hash'. It does not explain optional fields like fileId or fileSize, but the schema provides their types and constraints.

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 uses the specific verb 'registers' and identifies the resource as 'document attachments (metadata only — fileName + SHA-256 hash) on a draft notification request'. It clearly distinguishes itself from the upload tool by stating 'metadata only' and referencing notification_document_upload_url_create for actual byte uploads.

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?

Provides explicit timing ('Use once per batch of documents before activating'), a prerequisite ('Requires: notification_request_create → requestId'), and an alternative/exclusion ('call notification_document_upload_url_create for each registered attachment to get a URL to PUT the actual file bytes to').

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