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, and it states only that context compression is 'executed.' It fails to disclose that compaction is likely a mutating operation that alters or discards existing context, whether it is reversible, whether it requires an active session, or what the side effects on stored conversation history are. For a tool whose name implies data modification, this is a significant transparency gap.

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 and front-loaded with zero wasted words, which is structurally clean. However, brevity crosses into under-specification here — the single phrase earns its place but conveys almost no usable information beyond the tool name.

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 an action tool with a default-sensitive 'force' flag, no annotations, and no output schema, the description is severely incomplete. An agent has no way to know what compaction does to the LCM context, when forced compaction differs from automatic behavior, what the result of the operation is, or whether it is safe/reversible. It is inadequate for correct invocation and post-condition assessment.

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 100% — the 'force' parameter is already documented as '强制压缩' (force compression), so the schema carries the semantic weight. The description adds no further meaning about when or why force should be true versus false, but per the baseline rule, full schema coverage warrants a 3.

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 "[LCM] 执行上下文压缩" (execute context compression) is essentially an expanded restatement of the tool name 'compact' — it adds a generic verb and the resource 'context' but does not specify what compaction actually does to the context (e.g., summarizes, drops old messages, frees tokens). It does not distinguish the tool from its siblings beyond the obvious action-vs-query split, which an agent could already infer from 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?

There is no guidance on when to invoke this tool versus alternatives like lcm_status or lcm_search, nor any indication of when compaction is needed or when the 'force' parameter should be set versus letting the system act automatically. No prerequisites, exclusions, or sibling routing are mentioned at all.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only operation by saying 'list', but does not disclose whether it requires permissions, returns a large payload, or has any side effects. For a tool with no annotations, this is insufficient.

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?

A single concise sentence that front-loads the action ('列出所有') and the resource. No wasted words, and the purpose is immediately clear.

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 simple list tool with no parameters, no output schema, and no annotations, the description is minimal but functional. It lacks information about return format, potential size, or how it differs from lcm_search, which could be useful. Given the simplicity, it is acceptable but not thorough.

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 tool has zero parameters, so the schema already fully describes the input (none). The description adds no parameter details, but since there are no parameters, the baseline of 4 applies. There is nothing missing.

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 verb ('列出' = list) and a resource ('摘要节点' = summary nodes), clearly indicating the action. It distinguishes from siblings like lcm_search (which implies filtering) and lcm_compact (which implies modification), though it doesn't explicitly name them.

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. No mention of scenarios where listing all summary nodes is preferable to searching or compacting. The description only states what it does, not when to choose it.

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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only says 'search' and offers no information about return format, matching semantics, result scoping, or side effects.

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 concise sentence with the action and target stated directly. There is no filler, and the necessary core information is front-loaded.

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 no output schema and no annotations, the description alone should clarify what the agent receives and how this tool relates to its siblings. The one-line description leaves search semantics and result behavior ambiguous.

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 100% for the single query parameter, so the schema already defines it adequately. The description adds only the target scope (messages and summaries) without additional syntax or constraints.

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 that the tool searches within messages and summaries, which clearly identifies the verb and resource. It distinguishes from lcm_list_summaries (list vs search) but does not explicitly name sibling alternatives.

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 lcm_search rather than memvid_search or lcm_list_summaries. An agent must infer the appropriate context from the tool name alone.

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?

Annotations are absent, so the description carries the full burden. It only restates the name with a view/status phrasing; it does not disclose whether the operation is read-only, whether it has side effects, what the response contains, or how the maxTokens parameter affects behavior. No contradiction exists because no annotations are provided.

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 definition is a single short sentence with no filler or repetition, and the key action is front-loaded. It is trim, though the brevity causes information loss in other dimensions.

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 simple status tool with one optional parameter, the description names the outcome (view status) but does not say what fields or state are returned or what maxTokens is used for. No output schema exists, so that gap is noticeable but not disabling.

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 input schema covers maxTokens 100%, including a default and a Chinese description '上下文窗口大小 (默认 200000)'. The tool description adds nothing about how maxTokens changes the status calculation, so it stays at the baseline for full schema coverage.

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 names a concrete operation ('查看' / view) and a specific resource ('当前上下文状态' / current context status), so an agent knows what action to invoke. It does not explicitly contrast with siblings like lcm_compact or lcm_list_summaries, so it stops short of a top score.

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 given about when to use this tool versus lcm_compact, lcm_list_summaries, or lcm_search. The verb implies a status-check use case, but the description never states exclusions, alternatives, or prerequisites.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'check and restore' without explaining whether it mutates stored context, how it detects an interruption, whether it requires an existing broken session, or what side effects occur. The '[AUTO]' prefix hints at automation but does not clarify behavior.

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 front-loaded sentence that communicates the action and target context efficiently. The '[AUTO]' marker adds useful context without wasted words.

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 zero-parameter tool, the description conveys the general purpose well. However, with no annotations and no output schema, it leaves ambiguity about how the restoration is triggered, what 'interrupted' means in this system, and what the expected result is. An agent knows the broad intent but not the operational details.

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 tool has zero parameters, so there is no parameter information for the description to add beyond the empty schema. The baseline score of 4 applies because the description cannot meaningfully enrich 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 clearly states a specific action ('check and restore') and a specific resource ('previously interrupted conversation context'). This distinguishes it from sibling save/search tools by focusing on resumption. It stops short of 5 because it does not name any sibling or describe the restoration's scope.

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 phrase 'previously interrupted conversation context' implies the tool is for resuming after an interruption. However, there is no explicit guidance about when to use this tool versus alternatives like memvid_save_context or memvid_search, and no exclusions are mentioned.

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, the description must fully disclose behavioral traits. It mentions 'save' which implies persistence, and 'auto-generates summary' which suggests additional processing, but it does not specify side effects, permission requirements, reversibility, or what happens to existing data. The '[AUTO]' label is unexplained. This leaves significant unknowns for a mutation-like operation.

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 sentence with no redundancy or filler. It front-loads the core action ('quick save') and the unique feature ('auto-generates summary'). For a zero-parameter tool, this level of conciseness is appropriate, though it sacrifices completeness for brevity.

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?

Given the simplicity (0 params, no output schema), the description should still clarify the operation's impact and how it differs from memvid_save_context. It fails to explain what 'quick' means (e.g., no user confirmation?), whether the save is permanent, or any limitations. The tool's role in the broader workflow is unclear, especially with siblings like memvid_save_context and memvid_summary.

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 tool has zero parameters, so the baseline score is 4. The description adds no parameter-level detail, but since there are none, it does not need to. The schema is fully self-documenting for parameters (none exist), so this dimension is adequately covered.

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 clearly states a specific verb ('quick save') and resource ('current conversation context') with an auto-summary feature. However, it does not differentiate from the sibling tool memvid_save_context, which likely overlaps in functionality. The '[AUTO]' prefix hints at automation but adds ambiguity rather than clarity.

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 use this tool versus memvid_save_context, memvid_summary, or other siblings. The description does not mention any prerequisites, typical use cases, or exclusions. An agent would have to infer when 'quick save' is appropriate without explicit direction.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only says 'save' (保存), which implies a mutating write operation, but does not disclose whether repeated saves overwrite previous context, whether the action is reversible, what storage limits exist, or what the effect on existing state is. There is no mention of side effects or return behavior. This is a significant transparency gap for a state-changing 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?

The description is a single concise sentence that conveys the core purpose and usage context without any fluff. It is front-loaded with the action and resource. It earns every word and is appropriately sized for the tool's simplicity.

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 save-context tool with 3 parameters (1 required) and no output schema, the description provides the essential purpose. However, given the absence of annotations and the tool's mutating nature, it would benefit from more context about what gets saved, whether it appends or replaces, and whether there is any confirmation. Still, the tool is simple enough that an agent can infer typical behavior, so a middle score is appropriate.

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 100% — every parameter (topics, summary, projects) already has a descriptive comment in the input schema. The tool description adds no additional meaning or usage hints for the parameters. Per the rubric, baseline is 3 when coverage is high, and the description does not enhance parameter understanding 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 action ('保存' = save) on a specific resource ('当前对话上下文' = current conversation context), with the purpose '用于意外中断后恢复' (for recovery after unexpected interruption). This clearly identifies what the tool does and, implicitly, why it exists. It does not explicitly name sibling alternatives, but the purpose distinguishes it from search/compact/list tools in the sibling list.

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 a clear usage context: it is for saving context to recover after an unexpected interruption. This tells the agent when to use this tool. However, it does not state when *not* to use it or explicitly mention alternatives like memvid_quick_save or memvid_store, which may overlap. The guidance is adequate but lacks explicit exclusions.

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?

No annotations are provided, so the description carries the full burden of disclosing behavioral traits. It only says 'search long-term memory' and provides no details about read-only semantics, result format, pagination, or side effects.

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 concise sentence with no wasted words, and the core purpose is front-loaded. While it is notably sparse, it avoids redundancy and is structurally efficient.

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 two parameters, no output schema, no annotations, and no usage guidance, the description is far from complete. An agent would not know what results look like, how the search behaves, or how to differentiate this tool from the similarly purposed lcm_search.

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 input schema already documents both parameters (query and limit) with descriptions, and schema coverage is 100%. The tool description adds no additional parameter-level meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

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 clear action ('search') and target resource ('long-term memory'), so the tool's basic function is identifiable. However, it does not distinguish this tool from the sibling lcm_search, which likely targets the same resource, so it is not fully differentiated.

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 gives no guidance on when to use memvid_search versus alternative memory tools such as lcm_search, lcm_list_summaries, or memvid_store. No conditions, exclusions, or preferred scenarios are mentioned.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'store,' giving no information about persistence guarantees, idempotency, overwrite behavior, potential side effects, or whether the operation is reversible. For a mutation tool, this is a notable gap.

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, focused sentence with no filler. It front-loads the core action and resource, then gives clarifying examples. Every word earns its place.

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 straightforward store operation with a well-documented schema, the description is mostly sufficient. However, it does not address return values (no output schema exists), nor does it distinguish this tool from sibling memory-saving tools like memvid_save_context and memvid_quick_save, leaving some contextual ambiguity.

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 100%, so the input schema already documents all four parameters (tags, content, category, importance). The description adds context through examples of content types but does not meaningfully elaborate on parameter semantics beyond what the schema provides, warranting the baseline score.

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 clear verb and resource: '存储一条长期记忆' (store a long-term memory), with concrete examples like user preferences, project information, and technical decisions. It is unambiguous, though it does not explicitly differentiate itself from sibling tools such as memvid_quick_save or memvid_save_context, so it loses a point.

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 examples and the phrase '长期记忆' (long-term memory) provide clear context for when this tool is appropriate, implying it is for durable storage rather than transient data. However, it does not state exclusions or name alternatives like memvid_quick_save, leaving some routing to inference.

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?

No annotations are present, so the description carries the full burden. It only implies a non-mutating read operation but discloses no side effects, output format, or edge cases. This is minimal behavioral disclosure.

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 short sentence with no wasted words, making it concise. However, it is so minimal that it verges on under-specification, preventing a higher score.

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 no output schema and no annotations, the description should explain what the summary contains, how it differs from sibling search/list tools, or what the agent can expect. It does none of this, leaving significant gaps.

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 tool has zero parameters, so there is no parameter semantic burden. The schema is effectively complete with an empty properties object, and the description need not add parameter detail.

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 '获取记忆和上下文摘要' clearly states the tool retrieves a memory and context summary. The verb and resource are specific, but it does not differentiate from sibling tools like memvid_search or lcm_list_summaries, so it loses a point.

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 given on when to use this tool versus alternatives. With many overlapping sibling tools, the description provides no routing cues or exclusions, leaving the agent to guess.

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