check_assumption

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

With no annotations, the description carries the full behavioral burden. It discloses that the tool checks contradictions, scores risk, requests human approval, and stores per-project decisions. Still, it does not explain what happens after approval, whether the tool can block execution, or what side effects it has beyond requesting approval.

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 reasonably concise and well-structured: a summary sentence, a critical parameter directive, then bulleted usage triggers. The 'MUST call at every decision point' framing is slightly repetitive with the following bullets, but overall it earns its place.

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?

The usage context is strong: the description clearly says when to invoke the tool and stresses per-project storage via project_root. However, with no annotations and 0% schema coverage, the missing parameter semantics and ambiguity around the approval/contradiction flow leave the agent under-informed for a 6-parameter 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 description coverage is 0%, so the description must compensate for six parameters. It only explicitly explains project_root and implies assumption; context, category, risk_level, and alternatives receive no semantic guidance. This is a significant gap for an agent deciding how to populate those 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 opens with a specific verb and resource: 'Verify an assumption against past decisions.' It clearly distinguishes the tool from siblings by adding behavioral details—checks for contradictions, scores risk, and requests human approval—which separates it from query_decisions and ask_human.

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 gives explicit trigger conditions with 'The AI MUST call this at every decision point' and a bulleted list of when to use it. It also gives a mandatory project_root instruction. However, it does not name sibling alternatives or provide when-not-to-use guidance, so it falls short of a 5.

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