scan_binary_mitigations

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

With no annotations, the description carries the full burden, and it does disclose the analysis surface (mitigation flags plus a list of risky imports) and implies a read-only inspection. It does not say the file must be locally reachable, whether the binary is ever executed, what happens on an unsupported format, or how errors surface.

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 short clauses, front-loaded with the core action and the enumerated checks; nothing is padding. Minor awkwardness from the mid-parenthetical line break, but the information density is high.

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 one-parameter read-only scanner with no output schema, the description covers what is inspected but not the shape of the result (per-mitigation booleans? a verdict?) or the path contract. Adequate but leaves real gaps an agent must guess at.

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 0% — the single required 'path' parameter is documented only by its title. The description implies the path points at a binary of a specific format but never says whether it is a local filesystem path, absolute vs relative, or a remote/upload target, so it does not compensate for the coverage gap.

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?

Specific verb ('Check') plus a precisely enumerated resource: NX, PIE/ASLR, RELRO, stack canary, CFG, plus imported memory-corruption functions on ELF/PE/Mach-O binaries. That is far more concrete than the sibling names alone (full_audit, scan_strings, scan_secrets). It stops short of explicitly differentiating itself from full_audit or scan_apk, which likely overlap.

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?

Usage is only implied by the file-format list (ELF/PE/Mach-O), which narrows the applicable scope but never states when to prefer this over full_audit or scan_apk. No prerequisites, no exclusions, no named alternative.

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