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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false; the description adds that an AI model picks the queries and that results come back as evidence plus explanations. It does not disclose cost, latency, determinism (why readOnlyHint is false for something that appears to only read the graph), or whether the planned queries can affect state, which is the one behavioral question an agent most needs answered here.

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 sentences with no filler, front-loaded with the core action and followed by the return contract. It is efficient, though the second sentence is generic enough that a few words of routing detail would have been a better use of space.

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 two-parameter tool with full schema coverage and an explicit note about what is returned, the definition is mostly sufficient, and no output schema means return values need not be detailed. However, the unexplained readOnlyHint=false on an evidently read-oriented AI query planner leaves a real gap an agent cannot resolve from the description.

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 description coverage is 100%, so both parameters are already documented in the schema and the baseline is 3. The description only implies that `prompt` is free-form natural language and that `work_item_id` scopes the investigation to a work item; it adds no syntax, length, or scoping guidance beyond the schema.

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 uses a specific verb-plus-resource ("select and execute graph queries") qualified by an AI-driven planner and a domain (safety-coverage or traceability investigation). It is clear what the tool does, but it never mentions the obvious sibling run_graph_query, so an agent cannot tell from the description alone which of the two to pick.

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: "for a natural-language safety-coverage or traceability investigation" suggests when the tool fits, and "for human review" hints at the output's purpose. There is no explicit when-not condition and no named alternative (run_graph_query, traverse_pspp_graph) to route against, leaving selection to inference.

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