memory_evolve

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

There are no annotations, so the description must carry the behavioral burden, but it only names operations such as GC and revision without disclosing side effects, destructive potential, permissions, or return behavior. The label 'GC' implies deletion/cleanup, yet this is never stated explicitly.

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 text is extremely short with no filler, but it is under-specified rather than appropriately concise: a list of acronyms and operation names is not a structured explanation of the tool. It is compact but not optimally front-loaded for decision-making.

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?

This is a complex multi-action tool with 10 parameters, no annotations, and no output schema, yet the description provides only a fragment-level list of operations. An agent cannot determine required parameters per action, expected effects, or result formats, so the context is critically incomplete.

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% across 10 parameters, and the description does not mention code, tags, query, title, content, repo_path, supersedes, entity_type, or linked_symbols at all. It names a few actions but gives no mapping between parameters and actions, leaving the agent without usable parameter semantics.

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 identifies a semantic memory resource and lists several operation names (search, persist, distill_global, query_global), which is more than a bare tautology. However, it lacks a main verb and uses unexplained jargon (AGM revision, GC), and the tool's 'evolve' purpose is only implied by the name.

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?

No guidance is provided on when to choose this tool over its siblings (cpg_query, rlm_execute, swarm_blackboard) or when to use one internal action over another. The phrase 'Semantic memory' hints at context but offers no conditions, exclusions, or alternatives.

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