supersede_fact

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

No annotations are provided, so the description fully covers behavioral disclosure. It explains that the old fact stops appearing in current queries but remains queryable as-of past dates, and that the correction is recorded in the audit chain. This gives the agent complete understanding of the tool's effects and side effects without contradiction.

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 concise at about 100 words, front-loading the core action ('Supersede a fact...supercede-NOT-delete'), followed by usage guidance and parameter explanation. Every sentence adds value, with no redundancy or fluff. The structure is logical and easy to parse.

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 tool has an output schema (so return values need not be described) and 3 parameters, the description is remarkably complete. It explains the behavioral impact (queryability, audit chain), provides a usage scenario, and references related tools (facts_at_time). No critical gaps are present; the agent can use this tool correctly without additional context.

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?

With 0% schema description coverage, the description must explain parameters, and it does for the two required ones: relationship_id is the old fact's ID, superseded_by is the newer fact's ID. The optional 'reason' parameter is not explained, but its purpose (a reason for supersession) is reasonably inferable. This adds significant meaning beyond the bare schema, though one parameter remains undocumented.

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: supersede a fact with a newer one, explicitly contrasting with delete. It provides a concrete example ('ServiceX uses Postgres' → 'ServiceX uses MySQL'), making the function immediately understandable. The sibling tool 'supersede' exists but this is specifically for facts/relationships, and the description differentiates it from delete.

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 includes a direct 'USE THIS WHEN' clause with a concrete example, specifying exactly when to invoke this tool (correction of a fact). It clearly states the required parameters and their roles (old relationship_id, new fact's id as superseded_by), and references facts_at_time for obtaining relationship_ids, providing clear actionable guidance.

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