shadowgraph_search

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds non-obvious behavioral context: 'Schema keys never match, and a filter is never a content match' — an important guardrail for interpreting parameters. It could go further by noting pagination behavior, but the schema covers that.

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?

Four short sentences, each carrying information. The purpose is front-loaded, sibling distinctions are compact, and the read-only and filter semantics are stated in one concise clause. No filler or repetition beyond a harmless 'Reads only' echo of the annotation.

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?

Given a full input schema, output schema, and read-only/idempotent annotations, the description provides the missing high-level context: what counts as a match, how filters behave, and how this tool differs from the nearest alternatives. It is sufficient for an agent to select and invoke the tool correctly.

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 the baseline is 3. The description adds cross-cutting meaning beyond individual parameter descriptions, especially the rule that structured filters are never content matches and that all query terms must appear in declared content fields. This helps an agent avoid misusing kind, status, sourceClass, and minConfidence.

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 opens with a specific verb and resource: 'Find decisions, attempts, and facts whose declared content fields contain every query term.' It also distinguishes itself from siblings by naming shadowgraph_retrieve, shadowgraph_recall, shadowgraph_context, and shadowgraph_traverse with their respective behaviors.

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?

The description explicitly contrasts this tool with four sibling tools: retrieve adds one-hop neighbours, recall fuses ranks over scoped memory, context builds a working set, and traverse walks from an id. It also states 'Reads only,' helping an agent choose it over mutating alternatives.

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