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

Annotations already declare non-read-only, idempotent, non-destructive, open-world. The description adds valuable context beyond them: activation requires consent plus explicit user approval, and runs are bounded by per-run and monthly caps. That consent/approval gate is real behavioral information not present in the annotations.

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?

Two dense sentences, front-loaded with the core action then the gating requirements. No filler, though the consent clause could be slightly more explicit about consequences.

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 8-parameter mutation tool with 0% schema description coverage, the description covers the important gates (consent, approval, caps, timezone, frequency) and there is an output schema so returns needn't be explained. It still omits meaning for several params (idempotencyKey, active flag, brandId), leaving gaps for a 7-required-param save operation.

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 load and only partially does: it clarifies that the quote must be 'accepted', that timezone is explicit, and that runCap/monthlyCap are per-run and monthly limits, plus frequency is daily/weekly. It leaves brandId, idempotencyKey, active, hour, and weekday semantics unexplained.

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 (save) and resource (research schedule) and adds scope detail (daily/weekly, tied to an accepted quote, with timezone and caps). This distinguishes it from read/control siblings like list_research_schedules and control_research_schedule, though it doesn't name them explicitly.

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?

It gives a prerequisite gating condition (activation needs intelligence:run consent and explicit user approval), which implies when it's valid. However, it never says when to use this versus control_research_schedule or how it relates to quote_research/start_research, so routing is left to inference.

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