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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is known. The description adds two pieces of behavioral context the annotations cannot: the per-workspace uniqueness constraint on names and the fact that the call 'May return `needs_confirmation`', which prepares the agent for an unusual response shape.

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 verb and resource, then precondition, then trigger, then response caveat. Every sentence adds a distinct, actionable fact with no filler.

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 mutation tool with no output schema, the description covers purpose, prerequisite, trigger, and one return-value caveat, which is nearly everything needed. It omits permission requirements and what the created metric's identifier looks like, a minor gap given the annotations already cover the safety profile.

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?

With 88% schema description coverage the schema already documents most parameters, so 3 is the baseline. The description earns above that by defining the `name` concept ('a number the workspace watches') and stating its uniqueness scope, information the schema itself does not convey.

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 states a specific verb and resource ('Create a metric') and grounds it with concrete examples (triage time, weekly signups, cost per run), so the agent knows exactly what is produced. It does not, however, differentiate from sibling creators like ledger_metric_presets_adopt or ledger_metric_starters_adopt, so a one-line distinction is missing.

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?

'Check ledger_metrics_list first; names are unique per workspace' gives a concrete precondition, and 'When a user says they want to track or measure something, offer this' supplies an explicit trigger condition. It stops short of naming when NOT to use it versus preset/starter adoption tools, so it is clear context without exclusions.

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