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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds policy context like 'Doctrine: no_money_no_service' and 'burn compatibility,' but these are more about commercial gating and legacy status than technical behavior. There is no contradiction with annotations, but the description does not disclose what actually happens when the tool is invoked (e.g., what a session cert is, whether it returns a token).

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 short (two sentences) but uses cryptic, informal jargon like 'OFF TABLE,' 'burn compatibility,' and 'Doctrine.' While it front-loads the critical legacy status, the lack of clarity and structure makes it less effective than a clean, straightforward explanation. It is concise in word count but not in communicative efficiency.

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?

For a one-parameter tool with an output schema, the description still under-specifies functionality. It never explains what a 'Session Cert' is, what 'burn compatibility' requires, or what the tool actually returns. The heavy focus on deprecation and pricing leaves gaps for an agent trying to understand the tool's behavior and prerequisites. The output schema may cover return values, but the description does not provide enough operational context.

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% for the single parameter agent_id, described as 'Agent or wallet id that will own the session.' The description adds no additional meaning about the parameter syntax, format, or constraints. Baseline of 3 is appropriate because the schema fully documents the parameter.

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 what the tool does; it focuses on its legacy/deprecated status ('LEGACY / OFF TABLE') and commercial positioning ('$0.25 / 10') rather than a specific verb+resource. The title 'Session Cert' and name 'sqlguard_session' hint at issuing a session certificate, but the description never explicitly describes the function. It is closer to a deprecation notice than a purpose statement.

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 explicitly tells the agent when NOT to use this tool and provides clear alternatives: 'Prefer sqlguard_challenge → Exact Pilot unlock $100 or Gateway invoice $299+.' It also states 'Endpoint kept for burn compatibility only,' which clearly defines the only use case. This is excellent guidance that distinguishes it from siblings.

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