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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses blast radius ('Every saved query linked to it shows the new version immediately'), timing ('Applied when this runs'), and an approval-card obligation for the reason field. This is exactly the kind of consequence-level detail annotations cannot convey, and nothing conflicts with them.

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?

Three dense sentences, front-loaded with the mutability scope before the workflow instructions. Minor redundancy with structured fields (formulaId source repeated from the schema description), but no sentence is wasted.

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 a 7-param, nested-schema mutation with no output schema, the description covers the operation scope, sequencing prerequisites, and user-visible consequences. Its remaining gap is partial-update semantics — whether supplying only name leaves definition untouched — and nothing about the metrics array constraints, which an agent may need to fill correctly.

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 57%, and the description compensates by explaining that definition consists of expression and its own metrics, and by pointing formulaId at list_saved_formulas. The name/description/reason parameters are only obliquely covered ('Rename... change its description... explain it in reason'), and it does not say whether omitted fields are preserved, so it is good but not complete.

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?

The description names three concrete operations (rename, change description, replace definition) on a specific resource (saved formula) and clarifies that 'definition' means expression plus its own metrics. It is immediately distinguishable from create_saved_formula and delete_saved_formula 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?

It states a clear pre-call workflow: read via list_saved_formulas(formulaId) first, load the insight-queries skill first, and tell the user how many queries will change. It does not explicitly name when to use a different tool (e.g. update_query) or when this tool would be the wrong choice, so it falls short of full when/when-not/alternatives coverage.

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