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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true and openWorldHint=true, so safety and repeatability are covered. The description adds one genuinely useful behavioral caveat — 'passing means you ran the scan', i.e. a pass is not a clean bill of health — but says nothing about whether code is uploaded to a remote service, cost, or failure behavior.

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 tight, front-loaded sentences that each carry information, with the mode labels leading. The 'Q1'/'Q3' jargon is never defined, which costs a little clarity for a first-time caller.

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 4-parameter tool with no output schema, the description covers the two substantive inputs, their modes, and the pass/fail interpretation ('score and findings tell you what to fix'). The main residual gap is the unresolved overlap with pqc_scan_code and pqc_endpoint_check.

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 the baseline is 3; the description goes beyond it by binding `code` to Q1 and `endpoints` to Q3 and by stating the acceptance criterion (every endpoint must negotiate hybrid post-quantum TLS). It does not mention the agent_id/agent_token auth pair, but the schema documents those fully.

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 verbs and resources: 'scan your code for quantum-vulnerable cryptography' and 'check that every public endpoint negotiates X25519MLKEM768'. The dual Q1/Q3 scope is stated clearly, but nothing distinguishes it from siblings pqc_scan_code and pqc_endpoint_check, which appear to cover the same two jobs.

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 that supplying `code` drives Q1 and supplying `endpoints` drives Q3, but never says when to pick this tool over pqc_scan_code or pqc_endpoint_check. No exclusions, no prerequisites, and no mention of what happens if only one input is provided.

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