guard_read_file

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

Annotations already declare readOnlyHint, destructiveHint=false, idempotentHint, and closed-world, so the safety profile is covered. The description adds real value beyond that: sanitization happens in volatile RAM and the returned content is tokenized rather than raw. It stops short of saying how an agent recovers originals (presumably via reveal_text) or what happens if max_lines truncates content.

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?

A single dense sentence with the tool's identity and its two key behaviors (sanitize, return tokenized) front-loaded. No filler beyond the branding prefix, which is short enough not to obscure the action.

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 read-only five-parameter tool with full schema coverage and no output schema, the description covers what it does and what comes back (tokenized safe content). The main gap is the interaction with the masking workflow — an agent would not learn from this that unmasking requires a sibling tool.

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%, so every parameter including profile, sector, session_id, and max_lines is already documented in the schema. The description adds no parameter-level meaning at all — notably it never mentions the detection profile or session isolation, which materially change behavior. 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?

Names a specific verb and resource ('Reads any sensitive local file') and enumerates the file types covered (.env, config, credentials, .docx, .pdf, etc.), so the agent knows exactly what this does. It does not distinguish itself from close siblings such as sanitize_file, redact_file, or audit_directory_for_pii, so it stops short of a 5.

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 does state a usage preference ('Preferred over native file read tools'), which is genuine routing guidance, but the comparison target is outside the toolset. There is no guidance on when to pick this versus sanitize_file, redact_file, or guard_rag_chunk, and no stated exclusions.

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