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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which paint a safe, non-mutating picture. The description adds meaningful behavioral context by specifying that authority is 'not undeclared', that it is 'deterministic' and 'evidence-bounded', and that it produces a signed output. This clarifies the tool's safety and output nature beyond the annotations. Note: the 'without granting undeclared authority' phrase is a bit ambiguous but does not contradict 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?

The description is extremely concise: one sentence plus a small list of attributes. It front-loads the primary purpose and then lists key properties without any fluff. Every word contributes to understanding the tool's behavior and limitations. This is an example of minimal length with high information density.

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?

Given the tool has an output schema (not shown but present) and this is a special-purpose security tool, the description covers the core purpose and guarantees. However, it leaves out important context: it doesn't explain what constitutes 'transaction evidence', how the input should be structured (given the open schema), or how to interpret the signed result. An agent might be uncertain about the exact contract for invocation. The description is adequate but not fully complete for a tool of this complexity.

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?

The tool has 0 parameters in the description (though the input schema allows additional properties, meaning it accepts arbitrary input). With no parameters to document, the description has little to add on parameter semantics. The description mentions 'Bind an MCP tool call' which implies there is an input referencing the tool call, but it doesn't explain the expected structure of that input. Given the open schema and zero parameter coverage, the description could elaborate on what the input should contain, but it remains at a baseline level.

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 states the core function: binding an MCP tool call to transaction evidence, with specific characteristics (deterministic, evidence-bounded, signed). It goes beyond a simple verb+resource by highlighting the security guarantees. However, it does not clearly distinguish itself from the many sibling tools like transaction_assurance, payment_preflight, or mcp_2026_compatibility_gateway, which could plausibly overlap in purpose.

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 implies this tool is for when you need to bind a tool call to transaction evidence, but it does not explicitly state when to use this tool versus alternatives (e.g., transaction_assurance, proof_of_service). It lacks explicit exclusion criteria or references to sibling tools, so an agent might not know whether to choose this or another evidence-related tool.

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