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

Annotations declare readOnlyHint and idempotentHint, but the description adds substantial behavioral detail: text secrets are redacted, binary evidence is unmodified, images return native MCP images, and binary delivery has two modes with distinct trade-offs. This goes well beyond the annotations and helps the agent anticipate outcomes.

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 single dense paragraph that front-loads the core action and then systematically covers text vs binary behavior, delivery options, and parameter requirements. Every sentence adds operational value—no fluff or redundancy. The structure is logical and easy to parse.

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?

Despite the complexity of the tool (binary vs text, pagination, redaction, delivery modes, and output types), the description covers everything an agent needs: how to obtain evidenceId, how text and images are returned, how to handle binaries via link or base64, and the trade-offs of each. With no output schema, the description carries the full burden and meets it.

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?

Although schema coverage is 100%, the description adds crucial parameter semantics not fully captured in the schema: offset/limit are zero-based line pagination for text, byteOffset/byteLimit require binaryDelivery=base64, and binaryDelivery=link returns a resource_link to the authenticated original download. This clarifies how parameters interact and their practical implications.

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 clearly states the tool's purpose: 'Read attached evidence through MCP without changing its format.' It specifies the resource (evidence) and the action (read), and it explicitly tells the agent to 'Pass evidenceId from goal-get,' which ties it to the sibling goal-get tool. This differentiates it from other goal-* tools that create, attach, or modify evidence.

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 precise usage instructions: it explains when to use link vs base64, when byteOffset/byteLimit are required, and notes that base64 expands data and can consume context window, so 'use it only when needed.' It also instructs the agent on how to obtain evidenceId from goal-get. This is explicit when-to-use and when-not-to-use guidance.

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