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

Annotations already declare write/destructive/idempotent, but the description adds value beyond them: a send to a blocked number fails with FAILED.BLOCKED and still costs credits, and the block is irreversible through the API. That reversibility and cost detail is not available from the annotations. No rate limits or response shape described, so not a full 5.

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 dense sentences with the write marker and core effect front-loaded, then the consequence, then the irreversibility warning, then the endpoint. Zero 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?

With annotations covering the safety profile and no output schema to explain, the description supplies everything an agent needs: side effects, irreversibility, cost implications, and endpoint. Nothing material is missing for a single-parameter mutation tool.

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 100%, so the international-format example is already in structured data (baseline 3). The description adds the cardinality constraint 'ONE phone number,' which matters because the 'bulksms' name might otherwise suggest batch input, but it adds no format or validation detail beyond the schema.

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 and resource ('adds ONE phone number to the account's blocked list') and states the exact effect, including the endpoint (POST /blocked-numbers). It is immediately distinguishable from the read-side sibling bulksms_list_blocked_numbers.

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 gives an explicit trigger condition ('do it only when the user asks for it') and a strong exclusion backed by consequences ('This API has no way to remove a block again'). An agent knows when to call this and when to hesitate, with the reason spelled out.

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