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

The description contradicts the annotations. Annotations state idempotentHint=false and destructiveHint=true, but the description says 'Storing the same from/to/transform twice returns the same id' (idempotent) and 'does not touch either model' (non-destructive). This is a direct contradiction, so the description fails to align with the declared metadata.

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?

A dense single paragraph that front-loads the primary action and then packs exclusions, discoverability, and duplicate behavior with no filler. It could be split into sentences for readability, but every clause earns its place given the tool's complexity.

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 no output schema, the description adequately covers the return value ('the id this returns'), side effects (Relation recorded automatically), limitations (no validation/run), and discoverability. It references ROADMAP.md for deeper context. It does not elaborate on error conditions or the exact Binding structure, but the core call semantics are complete.

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. The description adds meaning by explaining the port-connection semantics ('fromModel's fromPort feeding toModel's toPort'), the transform field's free-text nature ('Not yet interpreted by anything'), and the content-addressed duplicate behavior. This goes beyond the schema's property descriptions.

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 states the specific verb 'Record' and resource 'an intended connection between two stored models' declared ports', clarifying it creates a content-addressed Binding. It distinguishes itself from sim_link by referencing 'sim_link's Relation graph' and explicitly frames the tool as a proposal that does not validate or run.

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 provides clear context on when this tool is appropriate: to create a non-validated, non-executed connection proposal. It also tells how results are discoverable (sim_edges, sim_get_binding). However, it does not explicitly name when to prefer sim_bind over sim_link or other siblings, nor state exclusions.

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