Witness

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

Annotations already cover readOnly=false, destructive=false, idempotent=false, but the description adds meaningful behavior: the witness is 'indeependently revalidted' and absence of a witness must fail closed. That is useful beyond structured fields. It does not describe side effects or output failure modes, but the fail-closed rule is a substantial disclosure.

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?

Two tight sentences with the core purpose up front and the critical decision rule second. There is no filler, repetition, or preamble. Every sentence adds value.

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?

This is a four-parameter tool with nested objects, 0% schema description coverage, and no output schema. The description states the goal and fail-closed stance, but it does not explain what the witness output looks like, what mode values imply, or what options are accepted. For an agent to invoke it correctly, more context is required.

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%, so the description should compensate, but it never mentions mode, old_schema, new_schema, or options. The parameter names and enum values provide partial clues about mode and schema comparison, but no explanation is given for option behavior or the exact meaning of each mode. This leaves the agent to infer too much.

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 names a specific action and resource: producing a backward-compatibility witness for JSON-Schema/MCP schemas before merge/deploy. The second sentence adds the key rule that UNKNOWN/NO_WITNESS_FOUND is not a compatible result, which clarifies the tool's intent. It falls short of 5 because 'witness' is domain jargon and no plain-language definition is given.

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 gives a clear temporal trigger: use before merge/deploy. It also advises treating unknown outcomes as incompatible, which helps the agent decide when to call the tool. Since there are no sibling tools and no when-not-to-use conditions, it stops short of a full 5.

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