graph_link

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

Annotations already declare this is a non-read-only, idempotent, non-destructive, closed-world operation. The description adds real behavioral context beyond that: re-running reconciles/closes stale edges, the operation both resolves and persists edges, and only repositories the caller may read participate (an authorization scope note). It does not disclose cost, duration, or what happens on partial failure.

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?

Two dense sentences, front-loaded with the primary edge-resolution behavior before the document-to-symbol phase and the permission caveat. No filler, though 'with both episodes' is opaque and slightly burdens reading.

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?

For a parameterless, output-schema-less batch recomputation, the description covers what is computed, what is persisted, idempotent re-run semantics, and permission scoping for the caller. Remaining gaps (runtime cost, dry-run availability, failure behavior) are minor.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly frames it as a workspace-wide batch operation requiring no arguments, though the phrase 'with both episodes' is unexplained jargon.

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 specific verbs and resources: resolving imports between independently indexed repositories by package identity, persisting cross-repository edges, and recomputing document-to-symbol links. An agent gets a precise picture of the operation. However, it never names a sibling or otherwise differentiates this write/compute tool from the many graph_* read tools around it.

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 implied rather than stated: 're-running after new episodes closes stale edges' tells the agent this is meant to be re-invoked after indexing, but there is no explicit when-to-use, when-not-to-use, or named alternative among the graph_* siblings. Adequate but leaves the agent to infer the triggering conditions.

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