ddflow_recall

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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains that results are labelled by kind and that a superseded decision names its replacement, which is specific output behavior. It also alludes to the cost of long answers in the max_chars parameter description, indirectly addressing context consumption. It does not mention read-only status or error handling, but for a search tool these are less critical. The disclosure is adequate and adds value beyond the schema.

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 longer than typical but every sentence serves a purpose. It opens with a memorable hook, states the primary function, gives an explicit usage directive, explains the rationale, and describes result labelling. It is front-loaded with the core purpose and does not include fluff. A slight deduction for length, but it remains efficient for 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a tool with no output schema, the description sufficiently explains what the agent gets back (results labelled by kind, superseded decisions pointing to replacements). It also explains when to call it and the context cost rationale. It does not describe pagination, error cases, or exact format, but these are minor for a search tool whose main value is the broad recall and guidance on timing. The description is complete enough for an agent to call it 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 coverage is 100%, so the schema already documents all four parameters with descriptions. The tool description itself does not add parameter-specific semantics beyond what is in the schema; the only added context about max_chars appears in the schema description, not the tool description. Thus, the description does not compensate for any gaps, but none exist, so baseline 3 is appropriate.

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 explicitly states the tool's function: a single search across all project memory (decisions, lessons, research, bugs, prompts). It distinguishes from siblings by emphasizing 'one search across everything,' whereas siblings like ddflow_lesson_search or ddflow_prompts are narrower. The verb 'search' and the scope 'everything this project remembers' are concrete and unambiguous.

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 direct, explicit directive: 'CALL THIS BEFORE STARTING ANY NON-TRIVIAL WORK.' It explains the rationale (avoid repetition) and clarifies how results should be interpreted (by kind, with superseded decisions pointing to replacements). It does not explicitly list when not to use it, but the 'non-trivial' qualifier implies trivial tasks may not need it, and the all-encompassing scope makes it the default recall tool.

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