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

The description explicitly claims 'Linking the same subject/predicate/object again as the same user ... is idempotent: it returns the existing relation's id ... rather than recording a duplicate edge', while the annotations declare idempotentHint=false. The text says the annotation is wrong, which is a direct contradiction an agent could act on. (The otherwise rich detail — auth, attribution, cost, immutability, refusal rules — cannot offset the conflict.)

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?

Purpose is front-loaded in the first sentence and almost every clause carries operational information (refusals, ownership, idempotency, cost). It is, however, a single dense paragraph with long semicolon chains that could be broken into predicate list vs. behavior, making it harder to scan than its content warrants.

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?

There is no output schema, and the description closes the loop itself by stating what is written ('one Relation, or nothing when it already exists') and the existing:true signal. Combined with the auth requirement, compute-token cost, attribution, immutability, and refusal semantics, an agent has everything needed to invoke and interpret this call.

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%, but the 'predicate' parameter has no enum in the schema, so the description carries the load: it enumerates every accepted predicate, gives each one's subject→object type signature, and specifies that 'object' is a /ns/models/v1 type name for @type and a content id otherwise. That is substantive semantics well beyond the field 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 opening sentence states a specific verb+resource+scope ('Record a typed edge between two stored entities ... using a registered predicate') and immediately distinguishes this tool from siblings (sim_bind, sim_supersede_model, sim_prove, sim_accept_migration) by naming the predicates each of those owns. An agent can tell exactly what this tool writes and what it does not.

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?

Usage is exhaustively specified: the valid predicate set is enumerated with subject→object type constraints, predicates refused here are listed together with the tool that records them instead, and 'narrower' is called out as the reversed form of 'broader'. It also states when the call will be refused and why (write rule / ownership).

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