whodb_platform_resource_graph

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds that the result is a 'normalized' graph, implying deduplicated/merged output, but says nothing about response size, pagination, truncation, or permission requirements for the caller. With annotations carrying the read-only/idempotent burden, a 3 reflects modest added context.

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, front-loaded with the core 'what' before the 'when,' and no filler beyond the resource enumeration. The second sentence is mildly dense but each clause carries information about targeting behavior.

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 must convey the return shape, and it does so at a high level ('normalized graph of resources and relationships') while the fields parameter documents nodes/edges/warnings. For a read-only, zero-required-parameter tool this is nearly sufficient, though the absence of any shape/scale detail for the returned graph leaves a small gap.

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 nodes, edges, warnings, workspace defaults, omit_files and omit_lineage are already documented in the schema. The description's 'Accepts workspace {host, org, project} for per-call targeting without changing defaults' largely restates the workspace schema description about session defaults. Baseline 3 is appropriate when the schema does the heavy lifting.

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 states a specific verb and resource: 'Return a normalized graph of hosted platform resources and relationships in the selected project.' It also enumerates the resource kinds included (sources, datasets, files, ontologies, functions, secrets, AI providers, lineage), which distinguishes it from single-resource siblings. However, it never names the closest alternatives (whodb_platform_project_resources, whodb_platform_workspace_map, whodb_platform_lineage), leaving the agent to infer the boundary.

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 a clear usage context: 'Use this when an agent needs to understand how ... relate before proposing changes,' which frames it as a pre-mutation reconnaissance step. It stops short of explicit exclusions or naming a sibling to use instead for narrower needs (e.g. lineage-only lookups).

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