stage_candidates

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

Annotations only say not read-only, not idempotent, not destructive, so the description carries the behavioral burden and does so thoroughly. It discloses candidate-count and string-size limits, relationship confidentiality rules, the ban on raw source text in candidate fields, SHA-256 based duplicate detection, and source_kind formatting constraints. No contradiction with annotations: the described write-and-detection behavior is consistent with readOnly false.

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 long but organized into semantic blocks: candidate types, constraints, confidentiality, evidence linking, and source receipt fields. It front-loads the core purpose before edge cases. A small amount of redundancy exists, such as the no-source-text rule stated more than once, but the density is justified by the tool's complexity.

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 complex 7-parameter tool with 0% schema descriptions and minimal annotations, the description supplies the operational essentials: candidate semantics, evidence-ref policy, disclosure behavior, size limits, and source handling. An output schema exists, so omitting return-value explanation is acceptable. An agent can select and invoke this tool correctly from the text alone.

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 coverage is 0%, and the description compensates substantially: it defines `source` limits, `source_kind` syntax, `content_digest` format and duplicate-detection role, `label` as the human-readable field, and trait evidence fields. However, `external_source_id` is never mentioned and the nested candidate structure is only partially specified, so not every parameter receives full treatment.

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 opening sentence names the verb 'Stage' and enumerates the exact resource types: people, interactions, affiliations, facts, observations, traits, and relationships. It also frames the distinct batching/provenance role, which separates it from the individual record_fact/record_observation/record_trait siblings.

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 gives an explicit trigger: 'Use this after extracting concise candidates from user-provided notes, meeting transcripts, or other agent-visible text.' It does not explicitly name alternatives or state when not to use it, but the context is clear enough for routing.

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