check_tool_result

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open world), yet the description adds genuinely new behavioral facts: execution is always local and content never leaves the machine, and the return value is the original content with secrets redacted or neutralized when an injection is found. That transformation/return behavior is not derivable from any structured field.

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?

Three sentences, front-loaded with the core purpose, then the privacy guarantee, then the return contract. Every sentence carries distinct information and there is no filler or repetition of the title.

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?

With no output schema, the description carries the burden of describing return values and does so (redacted content or neutralized content on injection detection). The remaining gap is the ambiguity of 'neutralized' — the actual returned shape or replacement text is not specified — plus no note on idempotency of repeated checks.

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% with only two required parameters, both already self-documented in the schema. The description mentions content categories (web pages, git commits, database queries) but adds no syntax, format, or interpretation guidance for 'content' or 'tool_name' beyond what the schema provides, so the baseline 3 applies.

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 (post-execution safety inspection), a specific resource (tool outputs and third-party content such as web pages, git commits, database queries), and a precise timing scope ('post-execution ... before LLM context assimilation'). That timing/scope framing implicitly separates it from the call-side sibling check_tool_call, so an agent can route between them without opening a schema.

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?

It states exactly when the tool belongs in a workflow: after a tool has produced output and before that content enters the model's context. However, it names no alternatives (check_tool_call, analyze_prompt) and gives no exclusions or 'when not to use' condition, which is what a 5 would require.

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