goodnotes_refresh_index

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description adds meaningful context beyond them: the index is private, work is chunked into bounded steps, jobId resumes the job, and force=true forces a full reread. "Does not change cloud notes" correctly reconciles the non-read-only hint with a non-destructive effect. What remains undisclosed is the lifecycle/status returned per call and what happens to the existing snapshot during a refresh.

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, front-loaded with the core action and followed by the resumption rule and the force/max-age behavior. Dense but no filler; only the trailing "Does not change cloud notes" could be tightened.

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 an eight-parameter, job-based indexing tool with no output schema, the description covers the control flow but leaves several parameters and the per-call return (job status vs. partial results) unaddressed. An agent could start a job but would be guessing on OCR/text-inclusion and scope parameters.

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 must carry the parameter burden, yet it only explains jobId, force, and maxAgeHours ("max age"). It says nothing about ocr, includeText, recursive, folderPath, or how maxSteps relates to "bounded steps", leaving five of eight parameters unexplained anywhere.

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?

"Build/resume a private recursive library index in bounded steps" gives a specific verb and resource, and "Does not change cloud notes" scopes it away from note-mutating siblings. It does not name which sibling to use instead (e.g., goodnotes_list or goodnotes_find_objects), so differentiation is implied rather than explicit.

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?

"Reuse jobId until complete" is real when-to-use guidance for the resume loop, and force=true's effect is stated. However, there is no guidance on when to reach for this index at all versus goodnotes_list or goodnotes_find_objects, nor prerequisites about the visibility of the metadata being indexed.

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