production.facial_reject

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

Beyond annotations, the description discloses that apply defaults to false (dry-run/plan by default), that 'the body Action is never modified', and that facial is an immutable plan.json reference — useful non-destructive guarantees and an error condition (TIMING_INPUT_REQUIRED). It is consistent with destructiveHint=false but adds real behavioral context annotations don't cover.

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?

It is reasonably sized but dense with internal jargon ('M7', 'NLA tracks', 'semantic mapping') and semicolon-packed clauses, and the opening sentence wastes space restating the tool name rather than stating purpose.

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?

An output schema exists, so return values needn't be explained, and immutability plus the speech error case are covered. But for a mutation tool with 7 undocumented parameters and no explicit statement of what is being rejected or on what evidence, significant gaps remain.

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% across 7 parameters, so the description carries the full burden. It only illuminates 'apply' (default false) and 'facial' (plan.json reference); brief, intent, object_name, operation_id, and options are entirely unexplained.

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 by restating the name ('facial_reject: M7 facial unit') and never states the actual verb — that it rejects/discards a candidate facial Action. The term 'Candidates are new Actions evaluated through NLA tracks' implies a candidate being rejected, but the specific reject operation is left to inference and never contrasted with the facial_accept sibling.

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 a workflow hint ('plan first, apply=false by default') and an error precondition ('Speech needs explicit timed phonemes... TIMING_INPUT_REQUIRED otherwise'), which help an agent sequence the call. However, there is no explicit when-to-use-this-vs-facial_accept/facial_refine guidance or exclusions, so usage is only implied.

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