Synap Memory

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

With no annotations provided, the description carries the full burden. It discloses the asynchronous behavior of extraction, states the tool returns processing status and memory count, and implies a read-only check. It doesn't discuss side effects or permissions, but for a status-check tool, the disclosure is strong.

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 three sentences, each adding distinct value: what it does, how to call it, and when to use it. There is no redundant information.

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 tool's simplicity (one parameter) and presence of an output schema, the description covers purpose, parameter origin, return values, and the rationale for using the tool. It's fully self-contained for an AI agent.

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 schema only provides the parameter name and type (string), with no description (0% coverage). The description fills this gap by specifying that the ingestion_id comes from log_exchange, giving critical semantic context that fully explains how to populate the parameter.

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 uses a specific verb 'Check' and clearly identifies the resource (a logged exchange's processing status). It also states the return values (processing status and memory count), distinguishing it from sibling tools that list, log, or recall memories.

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 explicitly instructs to pass the ingestion_id from log_exchange, linking it to a prior sibling tool. It also explains when to use it ('confirm a save completed') and why (asynchronous extraction), though it doesn't list exclusions or alternative tools.

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 carry the burden. It clearly implies a read operation via 'List,' but it does not explicitly state that it is read-only or describe what 'recent' means (e.g., time window, ordering). It adds some value by noting the debugging use case, but lacks depth on behavior beyond the obvious.

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 concise and front-loaded: two sentences that cover purpose and usage without redundancy. Every sentence 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?

The tool is simple (no required params, no nested objects) and has an output schema, so the description doesn't need to explain return values. It covers the core purpose and scoping, but could be more complete by addressing max_results and explicitly noting read-only behavior.

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 explains user_id/customer_id ('scope to one person') but does not mention max_results at all. Since schema coverage is 0%, the description should compensate more, but max_results is fairly self-explanatory from its name. It also leaves ambiguity about what happens if both user_id and customer_id are provided.

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 opens with 'List recent things remembered about this user,' which clearly states the action (list) and resource (memories). The additional note 'Useful for debugging or to confirm that memory is working' distinguishes it from sibling tools like recall_context, which likely serves runtime context retrieval.

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 explicit use cases ('debugging or to confirm that memory is working') and explains how to scope the query ('Pass user_id/customer_id to scope to one person'). However, it does not explicitly name alternative tools or state when not to use it, so it stops short of a 5.

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. It transparently discloses fire-and-forget default behavior and wait_for_processing as an opt-in confirmation flag. It also explains the behavioral implication of user_id/customer_id for memory separation. It doesn't mention error conditions or idempotency, but covers key operational traits.

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 well-structured paragraph. Every sentence adds operational value: trigger condition, payload content, user identification, and async behavior. No filler or redundancy.

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 presence of an output schema, return values need no explanation. The description covers all essential aspects: when to call, what to send, how to handle multi-user, and optional confirmation. Complete for a memory-logging tool.

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. It explains user_id and customer_id semantics (stable id per end-user/organization, omit for single-user) and the wait_for_processing flag. It does not clarify conversation_id, but the overall guidance covers most parameters meaningfully.

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 the tool's purpose: 'send the exchange here so it can be remembered' – a specific verb+resource. It distinguishes itself from sibling tools (check_memory_status, list_recent_memories, recall_context) which retrieve/manage memory, whereas this tool writes/logs exchanges.

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?

Explicitly instructs when to use: 'After each user message, send the exchange here'. It also provides exclusion guidance ('do not need to decide what is important') and alternatives/context by naming the sibling tools. Detailed guidance on user_id/customer_id and wait_for_processing further clarifies usage.

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 bears the full behavioral disclosure burden. It reveals some useful traits: the tool should be called proactively before replying, and user_id/customer_id scoping is important for multi-user environments. Yet it does not state whether the operation is read-only, what happens when no memory is found, or any rate-limiting or permission considerations.

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 two sentences with no wasted words. It front-loads the primary directive and follows with concrete usage instructions, making it easy to parse and actionable.

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 that an output schema exists, the description does not need to detail return values. The tool is straightforward, and the description covers invocation timing, query source, and user scoping. It is slightly thin on edge cases (e.g., what to do when no results), but for a retrieval tool of this simplicity it is largely adequate.

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. It adds meaning to the 'query' parameter (use the latest message) and explains user_id/customer_id selection for multi-user scenarios. However, it does not explain the 'max_results' parameter or elaborate on the relationship between user_id and customer_id beyond mentioning either is acceptable.

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 the tool's purpose: to recall user-specific information from past conversations before replying. It uses a specific verb ('recall') and resource ('anything already known about this user'), and the action is distinguishable from sibling tools like check_memory_status or list_recent_memories.

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 clear context on when to use the tool ('Before replying') and gives guidance on query construction ('Use the user's latest message as the query') and user identification for multi-user scenarios. However, it does not explicitly mention alternatives or exclusion conditions relative to sibling tools.

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