deja

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

Annotations are minimal (only openWorldHint), so the description carries the disclosure burden, and it largely succeeds. It explains the bracketed marker semantics (the user's later judgement that must be acted on), the 'déjà vu' citation format with session id, and the instruction to stay silent about unhelpful recalls. The remember mode's persistence side effect is disclosed ('store one durable decision so a later session can recall it'). Minor gap: no disclosure of retention limits or whether remember can overwrite prior notes, but no destructive behavior exists to warn about.

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 earns every sentence — for a six-mode, thirteen-parameter tool this density is justified. It is front-loaded with the core purpose and scope, then organized as a scannable mode list, then closes with result-handling behavior. No filler or repetition of schema content.

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 of this complexity, the description is remarkably complete. Every mode has a trigger, query semantics, parameter mapping, and result-handling protocol. It even covers the citation/acknowledgment behavior and the silent-failure rule, which an agent needs to interact correctly. No output schema exists, so the description appropriately covers result interpretation via the marker and citation guidance.

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 genuine value by mapping parameters to modes ('fix: the failing output, verbatim', 'how: tool or target', 'remember: one durable fact') and by giving query-strength guidance. The 'deja sources' reference for the harness enum and the note on multi-line error pastes go beyond the schema's terse descriptions.

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?

States precisely what the tool does: search a user's own past coding sessions across all their AI tools. It explicitly scopes itself against general knowledge and library docs ('only what happened on this machine'), which removes any ambiguity about what corpus is being searched. Each of the six modes is named and given a one-line definition, so an agent understands the full capability surface.

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?

Gives explicit when-to-use triggers for every mode: 'always before debugging an error or re-implementing something' for recall, 'when a recall hit is not enough' for context, 'before you edit, refactor or delete' for blame, 'you just hit an error' for fix, and 'Only after something is settled' for remember. The strongest query type is also specified ('an exact error string, function name or path is the strongest query'). No agent has to infer when to invoke this tool.

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