cloudflare_reconnaissance_prepare

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 real behavior: it writes three named artifacts and explicitly does not spawn agents or execute target code, which bounds the side effects. It omits where files land, what happens when the upstream validator rejects the ledger, and whether the operation is idempotent.

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 tightly packed sentences with the action and the output artifacts front-loaded and no filler. Dense domain jargon is expected here, but nothing is wasted.

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 an 11-parameter tool with nested objects, no output schema, and no annotations, the description is thin. Domain-specific fields like canonical_refs, ordinary_attack_class_block, excluded_blocks, and selected_companion_blocks are entirely unexplained, leaving an agent unable to construct a valid coverage_units entry from the description alone.

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 description coverage is 0% across 11 parameters, including deeply nested scout_reports and coverage_units objects, so the description must compensate. It only maps loosely onto two of them ('four scout reports' → the four required keys, 'coverage-ledger' → coverage_units) and says nothing about run_id, repository, target, source_ref, budget, profile, scope_paths, prior_run_paths, or selected_companion_files.

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?

States a specific verb and resource: synthesize four caller-supplied scout reports into run-metadata.json, architecture.md, and coverage-ledger.json. The negation 'does not spawn agents or execute target code' separates it from a wave-preparation sibling, though it never names which sibling consumes or validates its output.

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?

'Phase 1 adapter' plus 'caller-supplied' implies you must already hold four scout reports before calling, which is useful sequencing context. However, it never explicitly contrasts with audit_reconnaissance or cloudflare_coverage_ledger_validate, nor states what to do if validation fails.

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