memory_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 so well: it discloses return signals (`sufficient`, `missing`, `stop_reason`), escalation behavior in auto mode, and the ~4x cost difference between lite and full. It never states read-only status or result limits explicitly, and `max_items` semantics are unmentioned.

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 leading 'Adaptive recall' plus the sufficient/missing caution is front-loaded, and each sentence carries behavioral information. The mode parenthetical is dense with slash-separated shorthand, which costs some immediate readability but not enough to call it bloated.

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?

There is no output schema, and the description fills that gap by naming the key response fields and their meaning. Cost/capability tradeoffs across modes and the escalation path are covered, though the `max_items` cap and whether results can be truncated are not addressed.

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%, so the description must compensate, and it does thoroughly for `mode` (three named values with escalation logic) and `scope` (default project vs 'all'). It adds nothing for `query` or `max_items`, leaving one of four parameters entirely undocumented.

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 makes clear this is a memory retrieval tool that searches a scope plus global memory, and it details a mode-based search strategy. 'Adaptive recall' alone is vague, but the rest of the text supplies the specific verb+resource. It does not explicitly contrast with siblings such as memory_list, so it falls short of a 5.

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?

It gives real decision guidance: use 'full' when the answer joins several facts, use 'all' to search every project, and verify in code/docs when `sufficient` is false. It lacks explicit when-not-use guidance and does not name alternative sibling tools, so it sits below the top band.

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