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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: saving a cadence does not trigger an immediate check, and the default targeting when neither id is supplied. It does not cover permission requirements or the effect of switching an existing cadence to off, which keeps it from a 5.

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?

Front-loads the core action and its two enum outcomes, then layers the per-check parameter routing. Dense but every clause carries information; the only soft spot is the parenthetical '(neither means the primary site)', which is terse enough to require a re-read.

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, return values need not be explained, and the description covers scope, defaults, and the no-immediate-run side effect for a 4-parameter mutation tool. The dangling 'nextAt' reference is the one incomplete/ambiguous element in an otherwise self-sufficient definition.

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 baseline is 3, but the description adds real meaning the schema omits: the fallback to the primary site when neither trackerId nor siteId is passed, and the multi-market semantics of siteId for rank. It loses a point for referencing 'nextAt' as a parameter concept even though no such property exists in the input schema, which could mislead an agent into looking for it.

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?

Opens with a specific verb+resource ('Sets how often a rank check or site audit runs') and immediately enumerates the two possible values (off = manual only, weekly). The trailing 'Related: run_rank_check, run_site_audit' makes the boundary with the immediate-execution siblings explicit, so an agent can distinguish scheduling from running 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 concrete routing rules per check type: trackerId from get_rankings for a single market, siteId for all markets, neither for the primary site, siteId for site_audit. It also pre-empts a likely mistake with 'Saving a cadence never starts a check.' The only gap is that the related run tools are named but not given an explicit 'use X to run immediately' condition, leaving that inference to the agent.

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