update_sms_thread

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

There are no annotations, so the description carries the full burden. It supplies meaningful behavioral detail: append_tags toggles between adding tags and replacing the thread's entire tag list, empty notes are rejected, tags are capped at 100, account_id auto-resolves, and unknown lead_qualification values are passed through. It could further disclose mutation/reversibility implications or response behavior, but it is well above a minimal description.

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 front-loaded with the core purpose and sibling relation, then uses a clean Args block to enumerate parameters without redundancy or filler. Each sentence adds either purpose context or needed constraints; nothing needs to be cut.

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 7-parameter mutation tool with no annotations and an output schema present, the description is complete: it explains every parameter, key constraints, the append/replace semantic, and the relationship to update_call. Return values are covered by the existing output schema, so no extra return-format prose is needed.

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%, and the description fully compensates. Every parameter is explained beyond the raw schema: thread_id's source, notes length and empty-string rejection, value as numeric, tags count limit, append_tags flag behavior, lead_qualification's configurable values, and account_id auto-resolution. This is exactly the kind of parameter semantics an agent needs.

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: 'Update an SMS thread's lead-management fields.' It distinguishes itself from the closest sibling by explicitly framing itself as 'the texting equivalent of update_call' and by naming the exact gap it fills ('texting leads couldn't be tagged / noted / qualified via API'). An agent can identify what this tool does and how it differs from update_call without inspecting the schema.

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 clearly identifies the intended context: updating an SMS thread's lead-management fields rather than a call's, and points to update_call as the call-side equivalent. It does not, however, give explicit exclusions or a 'when not to use' statement, nor does it mention alternatives for read-only thread operations like get_sms_thread/list_sms_threads, so it falls just short of a 5.

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