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

Annotations already establish read-only, idempotent, closed-world, non-destructive, so the bar is lower — yet the description still adds substantial behavior: `derived` edges carry no link id and cannot be removed via delete_cross_link, links to trashed entities are omitted until restore, and links to hard-deleted entities vanish with them.

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 and scope are front-loaded and there is no filler prose; nearly every sentence carries behavioral information. The one waste is re-listing the full 19-value entityType enum, which the schema already enumerates verbatim, though the relation-type list is not in any schema and does earn its place.

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 carries the return-shape burden and does so: it enumerates relation types and notes that returned rows include the linked entity's name, type and module. It also covers the edge cases (derived edges, trashed endpoints, hard deletes) that would otherwise cause confused follow-up calls.

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% and both parameters are documented in the schema, so the baseline is 3. The description restates entityType's enum and entityId as a UUID without adding format, resolution, or lookup guidance, though 'ONE entity' usefully clarifies that a link endpoint must be a single record.

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 (list cross-module links on ONE entity), the direction scope (both directions), and exactly what each returned row carries (linked entity name, type, module, relation). It also names the relations it can return, so an agent knows this is the traceability graph rather than something narrower.

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?

Names two sibling alternatives and their differing scope: stride.get_story_context summarises parts of the graph for stories only, and story-to-story relations are a separate model handled by stride.list_story_relations. That gives the agent an explicit routing decision rather than requiring inference.

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