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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'opens 7d / 500 PASS' and 'Burn via POST /v1/session/cert + verify,' but these are unexplained and may even conflict with readOnlyHint (opening a window suggests a state change). No clear account of what happens, side effects, or required auth is given. The cryptic 'burn' step could imply destruction, but the description does not reconcile it with the non-destructive annotation.

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?

The description is a collection of fragmented phrases rather than a structured explanation. It is not front-loaded with the primary purpose; instead it leads with unclear references like 'Wealth Exact alt.' While it is short, the density of unexplained terminology makes it inefficient and confusing. Every phrase does not earn its place because most require external context to interpret.

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?

The tool has an output schema but the description is completely inadequate for an agent to decide when to invoke it. It fails to explain what a 'pilot' is, what '500 PASS' means, what the relationship to 'Wealth Exact' is, or what 'Burn via POST /v1/session/cert + verify' entails. The cryptic references to 'Session/Workday OFF TABLE' and 'Invoice alt $299/mo' leave the tool's behavior and domain almost entirely unexplained, making it impossible to use correctly without external documentation.

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% for the two parameters (agent_id, company), both with descriptions. The tool description adds no extra meaning about how these parameters relate to the pilot or how to set them. Baseline 3 is appropriate because the schema already handles parameter semantics; the description does not compensate with additional context.

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 does not clearly state a verb + resource. It opens with 'Wealth Exact alt' and 'Exact USDC $100.00 opens 7d / 500 PASS,' which is cryptic jargon. There is no explicit statement like 'creates a pilot' or 'activates a gateway.' It vaguely suggests an alternative or pilot, but the core purpose is obscured. It does reference sibling tools, but not in a way that clarifies its own role.

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 provides one explicit alternative: 'Prefer sqlguard_challenge when you have a DENY.' It also hints at exclusions with 'Session/Workday OFF TABLE as primary.' However, these are terse and assume domain knowledge. It does not clearly state when this tool should be used, prerequisites, or how to decide between it and other siblings beyond the DENY condition.

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