shadowgraph_record_fact

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

Beyond the annotations, the description discloses that a call supersedes the previous active fact while retaining history, that verification cannot be self-asserted, and that each call commits a revision. These are meaningful behavioral traits needed for safe invocation and are not redundant with readOnlyHint/idempotentHint/destructiveHint.

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?

Four short sentences, each earning its place: the core operation is front-loaded, followed by usage routing and key behavioral caveats. There is no filler or duplicated schema content.

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 the rich 100%-covered input schema and existing output schema, the description covers what an agent needs for selection and invocation: what a fact is, when to use it, how it replaces prior facts, and the verification limitation. Remaining details live in the schema where they belong.

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 schema already documents all 12 parameters. The description adds high-level framing ('claimed provenance class', 'optional validity window') but no detail beyond what the schema's sourceClass and expiresAt descriptions already provide, so the baseline applies.

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?

Description states a specific action ('Record one observed fact') with resource scope ('as a project and key') and distinguishes itself from shadowgraph_remember by defining the fact-key use case that triggers reopenWhen rules. This lets an agent select it correctly among the many record_* siblings.

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?

It explicitly says when to use the tool ('Use for the fact keys reopenWhen rules name') and points to the alternative for non-observations ('shadowgraph_remember stores durable memory that is not an observation'). This is direct when/when-not guidance rather than leaving selection to inference.

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