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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds substantive operational context: stateless execution, a 32 KB input ceiling, 60 RPM throttling, authentication paths ('?demo=true' or L402 at 50 sats), and a 400 on invalid input. These are call-planning facts an agent cannot derive from the annotations.

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?

Front-loaded with purpose and the sibling exclusion before operational details, and no sentence is filler. It is dense to the point of being clause-heavy in the second sentence (limits, auth, payment, error code all in one run-on), which slightly hurts scannability.

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 an output schema present, the description needn't explain return values, and it does cover limits, auth, and error behavior. The one unresolved gap is what happens to input exceeding 32 KB — truncation versus a 400 — which matters for a long-document summarizer and forces the agent to guess.

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% and the enum values are already documented, so the schema carries the parameter burden. The description merely restates that 'text' is the input and that 'summary_format' defaults to 'executive_bullets', adding no format semantics (e.g., when decision_log_table is preferable to one_paragraph_abstract). 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 ('Condenses') plus the exact resource classes it handles (technical specifications, RFCs, research papers, meeting transcripts) and the output artifact (high-density executive bullet points preserving figures and decisions). It also explicitly names the sibling it is not (synthesize_web_intelligence_brief), so an agent can route between the two without opening either 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?

Gives an explicit use condition ('producing a human-readable executive summary of a single provided document') and an explicit alternative with its distinguishing condition ('for researching a topic across the live web with Google Search citations, use synthesize_web_intelligence_brief instead'). The single-document vs live-web axis is exactly the decision boundary an agent needs.

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