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

Annotations already declare this is a non-read-only, destructive, non-open-world write, so the bar is lower, and the description adds real value: it requires explicit user approval, mandates a prerequisite status check, and enumerates data classes never collected (prompts, tokens, advertiser IDs, provider responses). It does not explain why destructiveHint is set or how idempotency affects repeat submissions.

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 sentences, front-loaded with purpose, then eligibility, then constraints; every sentence adds information. Slightly dense but no filler or repetition.

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 9-parameter, 7-required write tool with no output schema, the description covers purpose, gating, and privacy boundaries but omits how to obtain valid values for the enum fields, how idempotency_key should be formed, and what a caller gets back on success. It is minimally adequate rather than complete.

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%, so the description carries the full burden, yet it explains none of the nine parameters (task_stage, user_impact, observation_code, client, locale, idempotency_key, connection_context). 'Bounded classification fields' gestures at the enums but supplies no meaning or accepted values, and the 'never collects' list constrains content without defining any field.

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?

States a specific verb and resource ('Manually submit one tenant-scoped TikTok support_ref') plus the scope constraint ('bounded classification fields'). This is clearly distinguishable from the read-side sibling support_get_report_status, which the name and verb contrast with explicitly.

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?

Gives a concrete trigger ('When the user disputes data or numbers, use the most recent relevant successful result support_ref'), a prerequisite ('Read setup_get_status.support_reporting first'), and a gate ('after explicit user approval'). It stops short of naming alternatives or stating explicit when-not conditions beyond the 'never retries or replays' clause.

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