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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, yet the description adds real behavior: systems_in_scope is deterministic, the other two formats invoke the AI, and they are constrained to graph and transcript with production guardrails (no invented facts, no em dashes, short sentences). It omits auth requirements and latency/cost implications of the AI-backed formats, keeping it short of 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?

Three sentences, front-loaded with the core action before the per-format detail, and no filler. The parenthetical guardrails are dense but each clause carries distinct information.

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 supplies the return shape ({format, text}), which the agent would otherwise lack. Combined with per-format behavior, this is nearly complete; it stops short only on how an AI-format failure or empty transcript would surface.

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 the baseline is 3, but the description goes beyond the schema's terse 'The summary format' by explaining what each enum value actually returns. This meaningfully disambiguates the required format parameter beyond its schema text.

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 and resource ('Summarize a Wavelength flow') and then differentiates the three enum values by behavior, which lets an agent pick a format without guessing. It does not explicitly contrast itself with nearby siblings like review_flow or write_recaps, so sibling routing is left implicit.

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?

The description explains what each format produces, which implies when each is appropriate, but never states when to use this tool over alternatives such as write_recaps, review_flow, or ask_flow. Usage is inferable from the format semantics rather than stated.

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