fact_check_draft

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

No annotations are supplied, so the description carries the full behavioral burden, and it says nothing about whether flags mutate the draft, whether results are returned as a list, or what happens when no sources are attached. The required source attachment ('matching an attached source') is hinted at but never stated as a precondition or failure mode. An agent cannot tell if this is a read-only audit or a state-changing operation.

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 a single front-loaded sentence with zero redundancy, which is efficient. However, for a tool with three undocumented parameters and no annotations, this level of brevity leaves the definition under-specified rather than appropriately sized.

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 no annotations, no output schema, and 0% parameter coverage, the definition is too thin for a tool that presumably depends on attached sources and a draft identity. It leaves unanswered the central questions: what the return value looks like, whether the draft is modified, and what seed_id and channel do. The citation-rule core is clear, but the surrounding contract is not.

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 it does not. Nothing explains seed_id, the channel enum (newsletter/x/instagram/linkedin), or whether body is the text to scan or a draft reference. The only clue is the implied notion that body contains the sentences being checked.

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 states a concrete check: flag numbers, percentages, currency, and dates that lack a [S#] citation tied to an attached source. That is a specific verb (flag) plus a precise detectable condition, so an agent knows what the tool screens for. It stops short of 5 because it never contrasts with siblings such as approve_draft or mark_draft_ready, and the name 'fact_check_draft' suggests broader fact-checking than the narrow citation audit described.

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 statement of when to call this tool versus alternatives, no ordering relative to approve_draft or mark_draft_ready, and no prerequisite such as 'sources must be attached first'. Usage is only inferable from the word 'draft' in the name. No exclusions or workflow positioning are given.

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