ck_finding

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

No annotations are provided, so the description carries full burden. It discloses that it is a write operation (creates or updates DB record), that it is idempotent for the same rule_id within a session, and that it returns the finding ID, status, and ruling state. It also mentions the default decision and allowed values. However, it could be more explicit about potential side effects (e.g., overwriting existing findings) or the durability guarantee.

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?

The description is a single paragraph that is fairly concise and front-loaded with the main purpose. It packs significant information but could be more structured (e.g., bullet points for usage or examples). It is not excessively long and every sentence adds value.

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?

Given 9 parameters (5 required), no output schema, and complex governance semantics, the description is complete. It explains the conceptual role, required fields, defaults, and distinguishes from siblings. It also mentions return values (finding ID, status, ruling state) despite no output schema, which is sufficient.

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?

The schema already covers 89% of parameters with descriptions. The description adds value by providing examples and defaults: e.g., decision defaults to block, category examples (security/compliance/performance), severity examples (critical/high/medium/low), and rule_id format (CK-SEC-001). It also reiterates required fields.

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 clearly states the tool's purpose: 'Persist a governed finding with a ruling decision.' It uses specific verbs (persist, creates or updates) and resource (finding). It distinguishes from sibling ck_memory_record by specifying that ck_finding is for policy-related issues while ck_memory_record is for general knowledge.

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 explicitly states when to use: 'every policy check, validation failure, or human review should produce a finding.' It also provides guidance on when not to use by contrasting with ck_memory_record. Additionally, it explains defaults and exceptions (decision defaults to block; use allow for approved exceptions).

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