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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds two genuinely useful facts beyond them: results are aggregate 'Counts only' (no raw runs) and self-reported outcome totals are labelled. It says nothing about auth scope, rate limits, or latency for a metrics read.

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 telegraphic clauses with zero filler: subject, contents, a cardinality caveat ('Counts only'), and a safety tag. Front-loaded with what the agent gets back, no restatement of the title.

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 no output schema, the description carries the return-value burden and does so at a high level (run metrics, outcome totals, goals), plus the important caveat that values are counts and self-reported figures are flagged. It stops short of describing the shape or ordering of those counts, which an agent may want before calling.

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 100% – days (range, default) and agent_id (source of ids) are fully documented in the schema. The description's 'recent performance' loosely maps to the days window but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource: returns run metrics, outcome totals and goals for one agent. It clearly contrasts with write-side siblings like set_performance_targets, but never names list_goals, which it partially overlaps by including 'its goals'.

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?

No when-to-use or when-not-to-use guidance: it doesn't say how this differs from list_goals (goals are surfaced here too) or from probe_agent/validate_agent for the same agent. Usage is only implied by the tool name.

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