engram_recall

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

With no annotations, the description carries the full burden and does disclose meaningful traits: results are bounded ('the few'), superseded versions are deprioritised ('current versions first'), and an empty result is signalled by 'a note that nothing matched' rather than an empty list. It is silent on whether the call is read-only, on authorisation, and on cost/latency, which keeps it short of a 5 for an unannotated tool.

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?

Two sentences, no filler, and the operative constraint (call before answering) is not buried. It leads with the result shape and closes with the call condition, which reads efficiently for a two-parameter lookup tool.

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 two-parameter, unannotated, output-schema-less tool the description covers the important parts: result size, version ordering, and the no-match case. What is missing is the routing story against a large sibling set that also retrieves memories (engram_search, engram_check, engram_why), leaving the agent to guess which retriever fits which situation.

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 both 'message' and 'cwd' (including the project-precedence rule), making 3 the baseline. The description echoes the 'message' concept but never mentions 'cwd' or the effect of project scoping, so it adds nothing beyond 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?

The description states a specific retrievable resource (memories relevant to a message), with scoping (only 'the few clearly relevant') and ordering ('current versions first'), plus the empty-result behaviour. It does not differentiate itself from the retrieval-shaped sibling engram_search, so an agent must infer the boundary rather than being told it.

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?

'Call it before answering anything that may depend on past work, decisions or preferences' gives a clear positive trigger that is easy to apply. There are no exclusions and no named alternatives (engram_search, engram_check, engram_wake_up), so the agent is not told when *not* to use it or which sibling supersedes it.

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