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

Annotations are empty, so the description carries the full burden, and it delivers a lot: recurring monthly execution, a digest notification, the fact that monthly checks do not consume researches, quota limits per plan, and idempotent behavior on repeat calls ("returns its project"). It still omits the initial cost/credit implication of the first follow and any permission or reversibility notes, so it is strong but not exhaustive.

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?

Information-dense and front-loaded with the action, then mechanism, then limits and idempotency. Each sentence carries distinct facts (plan quotas, no research spend, repeat behavior), though the single long first sentence could be split for readability.

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 one parameter, no annotations, and no output schema, the description covers preconditions, side effects, recurrence, notification behavior, quotas, and idempotency. The only gap is what the call returns for a brand-new follow (the return value is described only for the already-followed case).

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 coverage is 100%, so the baseline is 3, but the description adds a real constraint beyond the schema: the referenced scan must be finished and must have a report. That eligibility nuance meaningfully refines how the single research_id argument should be chosen.

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 ("Starts following the niche of a finished scan") and then explains the resulting mechanism: the scan becomes the first measurement, monthly re-scans occur, and a change digest is emailed. An agent can distinguish this from siblings like run_signal, start_research, or get_report without opening any schema.

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?

Gives a clear precondition ("a finished scan that has a report") and a plan-capacity constraint (FREE 1, Starter 2, Pro 10), plus idempotency behavior when already followed. It does not explicitly name a sibling alternative or a when-not-to-use condition, so it stops just short of the top band.

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