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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety bar is lower; the description still adds real value beyond them. It defines the error-rate ratio (changes to plans, failed/unknown runs, failed audits over decided plans), the status thresholds (30+ decisions and under 1% to widen, over 5% to tighten), and the important caveat that counts are recorded events rather than verified customer outcomes. It also explicitly states 'Calls no model and starts no work.' The only gap is the absence of any return-shape/pagination detail, which is partly offset by the schema-level metric definitions.

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?

Content is information-dense and mostly earns its place, but the opening is a single unpunctuated mega-sentence cramming eight action families and six human dispositions into one clause chain, which hurts scannability. The later sentences (error-rate definition, status thresholds, category targets) are better structured and front-load nothing across the whole text.

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 burden of explaining return values, and it does so in unusual detail: per-family and per-action metrics, error-rate definition, statuses with thresholds, category rates against 95%/98% targets with gaps. For a read-only report tool this is close to complete; only window configurability and result size/pagination are unaddressed.

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% for the two required parameters (company UUID and environment enum), and the description compensates for neither — it never mentions company scoping or what staging vs production changes. The 14- and 30-day windows are described as fixed, which implicitly clarifies there is no time-range parameter, but that is the only parameter-adjacent information.

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 — read the calibration of Summer's autonomous "run it" decisions against actual outcomes, broken down by action and action family. It is highly specific about content (error rates, statuses, audit verdicts). It never names or distinguishes itself from plausible siblings such as summer_reports_autonomy_funnel, summer_autonomy_policy_preview, or summer_messenger_autonomy_read, so an agent cannot route between them from this text alone.

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?

Usage is only implied: the ready_to_widen / keep / tighten statuses hint that this is the report to consult before widening autonomy, but the description never says when to call it, when not to, or which sibling to use instead. The 95%/98% target framing suggests a decision-making context without stating one.

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