reply_draft

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

With no annotations, the description carries the full burden and does unusually well: it discloses grounding rules, citation-list output, MISSING_FACT markers for untraceable facts, that customer text is never a fact source, and that instruction-shaped messages are quarantined and reported rather than obeyed. It still omits whether the draft is persisted (a write side effect), whether it requires prior ingestion, and any permission or failure behavior.

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 tight sentences, front-loaded with the purpose and followed by the behavioral guarantees. No filler and every clause carries information.

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?

Behaviorally rich for a tool with no annotations and no output schema, and the citation/MISSING_FACT contract substitutes well for a return-value spec. However, for a 3-parameter tool with 0% schema coverage it leaves the parameters and any persistence side effect unexplained, which is a real gap for correct invocation.

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 three parameters, so the description must compensate and does not. 'ticket reply' weakly implies ticket_id, but draft_id (is it an existing draft to fill, or new?) and person_id (author? recipient?) are left entirely undefined, and required-vs-optional meaning is absent.

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 ('Draft a ticket reply') plus its core constraint ('ONLY from record facts, with a citation list'). It is clearly distinguishable from siblings like record_read/merge_execute by domain, though it never explicitly contrasts with them.

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?

There is no when-to-use guidance: no prerequisites (must records be ingested first?), no statement of when to prefer this over manually composing or over any sibling, and no exclusions. 'ONLY from record facts' is a constraint on output content, not routing guidance.

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