workflowmoves_audit_epk_timing

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

The annotations state this is not read-only and not idempotent, and the description adds real context beyond them: the call is asynchronous, returns a retained background job, and requires polling danceflow_job_status. The note that there are no base effect flags but that conditional inference/download effects must be checked via danceflow_component exposes a non-obvious permission nuance. It stops short of saying what retention means for repeat calls or whether earlier jobs are superseded.

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?

Four short sentences with the core action front-loaded and the follow-up actions after it, so nothing is buried. The telegraphic fragments ("Base effect flags: none.") read as clipped notes rather than prose but carry no wasted words.

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 an output schema present, the description need not describe the findings payload, and it correctly covers the async job lifecycle. Still, for a tool with a nested arguments object plus a six-flag permissions block, it leaves configured_urls undefined and does not say which permission flags this specific operation must acknowledge.

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?

Only half the parameters carry schema descriptions. The description mentions a "supplied HTML file" loosely covering html, but says nothing about configured_urls (up to 64 unique URLs) despite that being the one optional input whose meaning is least inferable. It also never ties the permissions flags to this operation, leaving the agent to read the nested schema description.

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?

"Find hardcoded EPK timing bindings in a supplied HTML file" gives a specific verb and resource, so the agent knows exactly what is scanned. It does not, however, differentiate itself from the nearby siblings workflowmoves_audit_epk_evidence and workflowmoves_audit_epk_layout, which scan related EPK concerns on presumably the same input.

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?

The description tells the agent what to do after calling (poll danceflow_job_status) and names danceflow_component for conditional inference/download effects, which is genuinely useful routing. It does not say when to choose this audit over the other EPK audits or what prerequisites the HTML must meet, so the primary when-to-use decision is left implicit.

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