ddflow_memory_add

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

With no annotations, the description carries the full burden and delivers: the log is committed (so 'Never put a secret here'), the entry is globally visible across worktrees, and writes are refused over a configurable [memory] max_chars (default 280). These are exactly the non-obvious behavioral traits an agent could otherwise violate.

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?

Front-loaded with the verb and scope, then alternatives, then constraints; every clause does work. It is dense with quoted examples and parenthetical tool names, which costs a little readability but no sentence is filler.

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 write tool with no annotations and no output schema, the description covers purpose, alternatives, visibility, refusal conditions and the secret hazard. It does not describe the success response (id/confirmation), though the check_only dry-run behavior is documented in the schema.

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 baseline is 3, but the description adds meaning the schema does not: the text must be a single fact and is length-capped, and the duplicate-refusal flow implied by `relation`/`check_only` is surfaced up front. It stops short of elaborating tag or as_agent semantics, which stay in the schema.

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?

Opens with a specific verb and resource ('Remember ONE operational fact about this machine, repository or working state') and immediately grounds it in three concrete examples. It explicitly separates itself from the three nearest siblings (lesson, session_note, decision), so an agent can route without opening any schema.

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?

States when to use it, when NOT to use it by naming the three alternative tools for each competing category (rules, events, architecture), and where the result surfaces (top of every ddflow_brief, searchable via ddflow_recall, shared across worktrees). Nothing is left to inference.

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