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

No annotations are provided, so the description must cover behavioral aspects. It doesn't mention side effects, performance, output format, or constraints like whether the code parameter is required. The description is too thin to disclose anything beyond the raw feature list.

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 extremely short, but this is under-specification rather than effective conciseness. It does not front-load key information about what the tool does or how to call it; instead it reads as a product tagline.

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?

With 4 parameters, a rich enum, no annotations, and no output schema, the description is vastly incomplete. It explains none of the modes, the meaning of depth, or the expected output, leaving an agent unable to use the tool correctly without external knowledge.

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%, and the description does not mention any parameters (code, mode, depth, symbol) or explain their roles. The enum values like blast_radius and def_use are self-explanatory, but no guidance is given for depth or symbol.

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 mentions specific analysis features like def-use chains, CFG, and blast radius, which suggests it's a code analysis tool, but it uses the vague metaphor 'radar' rather than a clear verb-resource structure. It doesn't explicitly state that it operates on code or what input it expects.

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?

The description provides no context about when to use this tool, what scenarios it fits, or any alternatives. Sibling tools are unrelated, and no exclusions are stated. An agent would have to infer that it's for code analysis from the feature list.

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

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.

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions several safety mechanisms (sandbox, transactional CoW rollback, linter, governor) which imply controlled side effects and validation. However, it does not specify whether the operation is read-only or mutating, what happens on error, or the nature of side effects beyond rollback. This is a moderate level of transparency given the short description.

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 a single, dense sentence that packs multiple salient features without fluff. It is front-loaded with the primary action ('Sandboxed RLM REPL executor') and immediately conveys key behavioral characteristics. Every word contributes value.

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 with three parameters and no schema descriptions, the description is severely incomplete. It omits an explanation of what RLM is, what each parameter means, what the return value looks like, and under what circumstances the tool should be used. The agent would have to guess at nearly every aspect of usage.

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?

The description adds no meaning to any of the three parameters (code, query, scope_paths). Since schema description coverage is 0% and the description never touches them, the agent receives no semantic context beyond the bare parameter names, which is insufficient for correct invocation.

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 specific action: executing RLM code in a REPL, and adds notable features (sandboxed, transactional CoW rollback, linter, governor). However, it does not differentiate this tool from its siblings (cpg_query, memory_evolve, swarm_blackboard) by explaining what distinguishes it or when to prefer 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?

The description provides no guidance on when to use this tool versus its siblings. It does not state conditions, prerequisites, or explicitly mention alternatives, forcing the agent to infer usage solely from the name and generic executor label.

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

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

With no annotations provided, the description alone must carry all behavioral disclosure. It fails to state side effects, mutability, persistence, per-action semantics, or requirements. Terms like 'OCC validation' and 'tree merge' imply operations but do not disclose whether state changes are destructive or reversible, leaving the agent entirely in the dark.

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 only one sentence, but it is not appropriately sized because it is dense with jargon yet empty of actionable meaning. It is under-specification rather than conciseness—every term could be omitted without loss since none are explained.

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?

The tool has 8 parameters, a complex action enum, nested objects, and no output schema, yet the description provides none of the necessary context for an agent to call it correctly. There is no explanation of expected payloads, return values, or interaction with the blackboard, making the tool effectively unusable without external knowledge.

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%, and the description makes no attempt to explain any of the 8 parameters or the action enum. The action values (out, rd, in, eval, etc.) are unexplained, and payload, read_set, write_set, and read_version have no semantic context. The description adds zero value beyond the raw 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 mentions 'Swarm blackboard & OCC concurrency' and lists algorithms (Kung-Robinson OCC, Tree-CRDT merge, Linda tuple space) but never states what the tool actually does for the caller or what resource it operates on. It reads as a feature list rather than a clear verb+resource statement, leaving the agent without a concrete purpose.

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?

There is no guidance on when to use this tool versus alternatives, when not to use it, or any prerequisites. The sibling tools are entirely unrelated (cpg_query, rlm_execute, memory_evolve), and the description provides no comparative context, so an agent cannot determine appropriate invocation.

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