memory_search_candidates

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat safety traits. It adds the behavioral trait 'provenance-bound,' which indicates results are tied to provenance, and recommends fetching original evidence—implying candidates are not full evidence. This adds some context beyond annotations, but lacks details on pagination, filtering, or result structure.

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 extremely concise at two sentences, with no wasted words. However, given the tool's complexity (5 parameters, multiple enums, sibling differentiation needed), the brevity feels underspecified. The second sentence is a useful instruction but does not compensate for missing parameter descriptions. It is efficient but not sufficiently informative.

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?

The tool has 5 parameters, no schema descriptions, an output schema, and 28 siblings. The description only covers the high-level purpose and a usage hint. It lacks parameter semantics, explicit differentiation from siblings, and behavioral details like result ordering or error conditions. The output schema exists but is not referenced. The description is incomplete for an agent to use this tool effectively without prior knowledge.

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 0%, meaning the description must compensate for undocumented parameters. However, the description provides zero information about the five parameters (query, mode, top_k, status, candidate_backend). Parameter names and defaults offer limited guidance, but the agent lacks semantic context (e.g., how 'mode' affects search, what 'status' filters). This is a significant gap.

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 'Return provenance-bound candidates,' which clearly identifies the tool's action (return) and resource (candidates). It implies a search function without explicitly naming alternatives, but the advice to 'Fetch original evidence before concluding' hints at differentiation from evidence-fetching siblings like memory_fetch_evidence. The purpose is clear but could better distinguish from memory_latest or other search tools.

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 a usage hint: 'Fetch original evidence before concluding,' suggesting this tool is a precursor to memory_fetch_evidence. However, it does not explicitly state when to use this tool versus alternatives (e.g., memory_latest, memory_search_candidates), nor does it specify exclusions or prerequisites. The guidance is implied rather than direct.

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