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

The description frames this as a pure read served 'from an index', and its only behavioral caveat is eventual consistency across instances. Annotations instead declare readOnlyHint=false, destructiveHint=true and idempotentHint=false; the non-idempotency is loosely supported by the re-listing sentence, but nothing in the description accounts for a destructive, non-read-only profile. It also adds genuinely useful semantic disclosure (unregistered axis, unwitnessed structural edges), so the conflict, while real, is partial rather than total.

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?

Front-loaded with the core purpose, then layered: indexing/consistency, legacy edges, structural edges, and the isomorphicTo caveat. Dense and long, but nearly every sentence carries decision-relevant information; the isomorphicTo paragraph is the one place that could be trimmed.

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 compensates well by explaining result semantics: the 'unregistered' axis for legacy predicates, 'unwitnessed' edges that prove nothing, and witness ids. Missing pagination/volume behaviour and any mention of ordering, which for an all-relations-of-an-entity query an agent would want.

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?

One required parameter with 100% schema coverage, so the schema already carries the meaning ('entity id to look up'). The description adds the nuance that the id matches against both subject and object positions, but no format or id-scheme guidance beyond that. Baseline 3 is appropriate.

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?

Opens with a specific verb+resource+scope: 'List every relation touching an entity, as either subject or object.' That scope statement distinguishes it from directional siblings like sim_neighbors, and the description goes on to define exactly what kinds of edges appear in the result set.

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 gives clear activation context ('each call re-lists the store so edges written by other instances are seen') and routes the agent to concrete alternatives for follow-up — GET /api/lineage/{witnessId} and sim_check_witness. It stops short of an explicit when-not-to-use statement, so it is a strong 4 rather than a 5.

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