kit-memory-demo

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

No annotations are present, so the description must carry the burden of behavioral disclosure. It does not mention any behavioral traits such as ordering, pagination, or permissions, leaving significant gaps.

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 wasted words. It is front-loaded and easy to parse.

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 of the tool (no parameters, no output schema), the description is adequate but lacks details about return format or scope. It meets the minimum viability but could be more complete.

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?

There are no parameters, and schema coverage is 100% (trivially). The description adds no additional parameter info, but the baseline of 4 is appropriate as no further details are needed.

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 'List' and a clear resource 'knowledge areas', leaving no ambiguity about its function. It differentiates itself from siblings like 'capture' or 'commit' which have different purposes.

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 explicit when-to-use or when-not-to-use guidance is provided. However, since the tool is a simple list with no siblings performing a similar function, the context implies it's for retrieving areas.

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 carries full burden. It explains the core action (extract and save drafts) but omits details like authentication needs, rate limits, or whether existing drafts are affected. The description is accurate but not richly transparent.

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, each serving a purpose: defining the action and specifying when to use. No wasted words; highly 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?

Given 6 parameters and 1 required, no output schema, the description covers the purpose and usage context adequately. It lacks details on return values but is sufficient for an agent to select and invoke the tool appropriately.

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 50% (3 of 6 parameters described). The tool description does not add additional meaning beyond what the schema already provides for the parameters. Baseline 3 is appropriate as the description does not compensate for undocumented parameters.

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 verb 'extract' and 'save', the resource 'candidate memories from a session transcript', and provides a specific use context. It distinguishes from sibling tools like 'remember' and 'note' by focusing on session transcript 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 explicitly states when to use: 'near the end of a meaningful session when the transcript contains decisions, gotchas, or reusable context.' It implies when not to use (no valuable content) but does not provide explicit 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?

No annotations provided, so description carries full burden. Only states it adds durable memory, but does not disclose idempotency, required permissions, deduplication behavior (despite related parameters), 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?

Two sentences, no filler. Front-loaded with the core action and usage guidance. Every word adds 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?

With 13 parameters, low schema coverage, no output schema, and no annotations, the description is insufficient. It does not explain return values, parameter effects, or process 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?

Schema description coverage is only 15%, and the description adds no explanation of parameters beyond the general purpose. Parameters like 'tier', 'scope', 'surface' have enums but are not clarified in description.

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?

Description clearly states verb 'Add' and resource 'durable memory to Kit's knowledge corpus', and specifies the type of content (stable decisions, facts, gotchas, patterns). It distinguishes from sibling tools like 'note' by emphasizing durability and searchability.

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 says when to use: for stable decisions, facts, gotchas, or patterns. Implies not for temporary or transient data. However, it does not explicitly exclude alternatives or mention when not to use.

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 fully disclose behavior. It only states the purpose and scenarios but fails to explain what happens after invoking the tool (e.g., is the handoff stored? Is it destructive? Can it be overwritten?). This lack of detail leaves the agent uncertain about 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, well-structured sentence that leads with the core purpose ('Write a concise handoff') and concisely lists trigger scenarios. No unnecessary 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?

The tool is simple and the description covers purpose and usage scenarios adequately. However, it lacks information about the handoff lifecycle (where it goes, how it's accessed later) and does not relate to sibling tools like recall or remember. Given no output schema, more context would be beneficial for an agent unfamiliar with the system.

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 covers 67% of parameters with descriptions (title, content, surface have descriptions; tags is partially covered; project and session_id lack descriptions). The tool description adds minimal detail beyond the schema, e.g., implying content should be concise. It does not compensate for the undocumented project and session_id parameters.

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 action (write a concise handoff), the resource (handoff for next agent/surface), and specifies exact scenarios when to use it (session end, topic change, completed work, long-session restart). This distinguishes it from sibling tools like note or commit.

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 explicitly lists four use cases (session end, topic change, completed work, restart point) providing clear guidance on when to use the tool. However, it does not specify when not to use it or contrast it with alternatives like note or commit.

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?

Without annotations, the description minimally covers behavior: 'writes a live operational checkpoint'. It does not explain side effects, idempotency, or what 'checkpoint' entails (e.g., overwrites or appends). More detail would be beneficial.

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?

Two sentences, very concise and focused. However, the structure could be improved by separating the purpose from usage guidance for better readability. Still, each sentence adds 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?

Given no output schema and no annotations, the description leaves ambiguity about what happens after writing (e.g., persistence, visibility). It tells when to use but not the full behavioral contract, missing completeness for a mutation 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?

With schema description coverage at 56%, the description adds only a hint about kind=handoff usage. For 9 parameters, this is insufficient. The required parameters' meanings are left to the schema, and optional parameters like project, collab, supersedes get no extra context.

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 writes a 'live operational checkpoint' for Kit-connected surfaces, with a specific verb and resource. It differentiates from siblings by focusing on checkpoints for thread handoff, and lists explicit use cases.

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 when-to-use scenarios (start, diagnosis, pivot, etc.) and when to use kind=handoff. However, it does not mention when not to use this tool or suggest alternatives among siblings.

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 carries the full burden. It indicates a read operation but omits any details about behavior such as authentication, rate limits, error handling, or response format. The description is minimal.

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 one concise sentence with no unnecessary words. It front-loads the core action and resource.

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 with one optional parameter, so the description is functional but incomplete. It does not describe the return value or output format, which is missing since there is no output schema.

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 already provides a description for the single parameter 'window_minutes' with defaults and limits. The description adds only the phrase 'within the requested window', adding minimal value 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 clearly states the verb 'Read', the resource 'live Kit facet presence', and the scope 'within the requested window'. It distinguishes itself from sibling tools like 'areas', 'capture', etc., which are different actions.

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 alternatives. The sibling tool names hint at different functionalities, but the description lacks explicit context for selection.

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?

Without annotations, the description carries the full burden. It implies a read-only retrieval operation but does not explicitly state that it is non-destructive or any authentication requirements. The description lacks explicit behavioral traits beyond the core function.

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, front-loading the purpose, then usage, then result. It is concise with no redundancy, though it could be slightly more compact without losing clarity.

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 retrieval tool with no output schema and no annotations, the description covers purpose, usage, and return value. It lacks details on error behavior or exact scope, but overall it provides sufficient context 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?

Schema coverage is 100%, so both parameters are already described. The description adds minimal value beyond what the schema provides, only restating the search context. Baseline is 3 as per guidelines.

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 verb 'Recall' and the resource 'Kit's knowledge' using semantic search. It distinguishes from siblings by specifying usage before answering user questions about the Kit, which contrasts with tools like 'capture' or 'note' that create new knowledge.

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 explicitly says 'Use before answering any user question about this Kit...' providing clear context for when to use this tool. However, it does not mention when not to use it or suggest alternatives, which would further strengthen this dimension.

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 for behavioral disclosure. It accurately indicates a read operation (non-destructive) but lacks details on auth, rate limits, or side effects. Adequate for a simple read, but minimal.

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 sentence of 12 words, front-loaded with the core action. Every word earns its place with no 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?

For a simple tool with one parameter and no output schema, the description is sufficiently complete. It explains the purpose and parameter origin, though additional context on return format or error cases could be helpful.

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 coverage is 100% for the single 'id' parameter. The description adds meaning by specifying the id is 'as returned by recall', clarifying the expected source beyond the schema's type and description.

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 reads a single memory by id, with a specific verb ('read') and resource ('Kit memory'). It distinguishes from sibling 'recall' by referencing that the id comes from recall.

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 implies usage when you have a memory id from recall, but does not explicitly state when to use versus alternatives like recall or capture, nor provides any 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?

Discloses behavioral traits such as the returned components (you_are, knowledge areas, tools, contract) and the non-imposing nature of the identity ('offered, not imposed'). Since no annotations are provided, the description fully carries the burden and does so thoroughly.

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 front-loaded with the critical instruction and then expands with necessary details. It is well-structured but could be slightly more concise; every sentence adds 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?

Covers usage, return values, identity handling, and differentiation from recall, but lacks parameter documentation. Given no output schema, the description does a good job overall, but the missing parameter information is a notable gap.

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 explain the 'scope' parameter (enum: work/personal/all). While the parameter is optional, the omission means the agent cannot infer its meaning from the description, which should compensate for the lack of schema descriptions.

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 be called first in every new chat to retrieve identity, knowledge areas, tool permissions, and the working contract. It uses a specific verb ('call') and resource ('Kit'), and differentiates from the sibling tool 'recall'.

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 to call 'FIRST in every new chat' and provides a when-not-to-use condition: 'For anything this Kit/customer/project/product should know, call recall first.' This offers clear context for use vs. alternatives.

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