web

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful behavior beyond annotations: broken links are omitted, archived/deprecated nodes are marked, and the return shape or Mermaid alternative is described.

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?

The description is front-loaded with the core purpose and then adds scope, exclusions, and return behavior. It is dense and includes section references (§6, §6.2, §5.1) that may be noise to an agent, but it is not verbose.

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 read-only graph tool with no output schema, the description supplies the return shape, mermaid mode, scope behavior, and omission/marking rules. It is nearly complete, though it could explicitly name the `bundle` parameter rather than relying on inference.

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?

With 0% schema description coverage, the description carries the full burden and explains all three parameters meaningfully: `bundle` via location behavior, `concepts=true`, and `mermaid=true`. It could be slightly clearer about the bundle argument itself and its default, but the functional semantics are largely covered.

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 clearly identifies the resource as a link/citation graph, stating that it shows which concepts link to or cite which. It distinguishes itself from lint by noting that broken links are excluded and reported by lint, but it does not explicitly distinguish itself from the sibling `links` tool.

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 by the scope behavior: root level shows bundles with edge counts, while a bundle or `concepts=true` shows concepts. The only explicit alternative is lint for broken links, but there is no direct guidance on when to choose `web` over `links`, `search`, or other inspection tools.

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