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

Goes far beyond the annotations: it enumerates every precondition (edge touches model, is offered, passes sim_link's check, ownership or authorship, target predicate's write rule), states atomic validation (all edges checked before anything is written; one failure writes nothing), describes partial-failure reporting, confirms the old edge survives, explains attribution/timestamps and migratedFrom provenance, and documents OAuth write scope, MCP-only availability, and the 1-compute-token cost. destructiveHint/openWorldHint give almost no detail on their own, so the description carries the load well.

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?

One dense paragraph, front-loaded with purpose followed by preconditions, then write semantics, idempotency, partial failure, auth and cost. Every sentence conveys distinct information, though the packing is heavy enough that a reader must hold several clauses at once.

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?

With no output schema, the description still covers return-relevant behavior: attribution to the caller, existing: true for reused links, migratedFrom provenance edges, and what a partially completed call reports. Auth, availability and cost are all stated, so nothing needed to invoke it correctly is missing.

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 baseline is 3, but the description adds real meaning beyond the schema field text: the 1–25 bound's source, that edges must touch model, be offered, and satisfy sim_link plus the predicate's write rule for the caller, and that successor is validated against the currently returned successor (a re-point or extended chain is refused rather than followed).

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 — carry a superseded model's offered taxonomic edges forward to its current successor — and names the exact upstream source (sim_migration_offers(model)) and the successor argument that selects the target. An agent can distinguish this from sim_link (creating new edges) and sim_supersede_model (creating the successor) without opening any schema.

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?

Makes the trigger clear: edges must be ones sim_migration_offers(model) offered, and successor must be the current one it returned, otherwise the call is refused. It also points to sim_edges and sim_query for verifying the result. It stops short of explicitly naming an alternative tool for the case where you want a different migration shape, so it is clear context rather than full when/when-not routing.

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