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

With no annotations provided, the description carries the full burden. It clearly discloses that the tool restores identity, ongoing work, and learned knowledge from previous sessions. However, it omits potential edge cases such as behavior when no previous session exists or whether current session state is overwritten, leaving some ambiguity.

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, consisting of two sentences. The first sentence states the action, the second provides usage timing and specific outcomes. Every word adds value 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 zero-parameter tool without an output schema, the description gives sufficient context: what it does, when to use it, and what it restores. It does not address failure scenarios or interactions with sibling tools, but this is not essential for basic invocation.

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, and the schema fully covers this (100% coverage). The description adds context about the tool's purpose but does not need to explain parameters since none exist. Baseline of 4 applies.

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 'restore' targeting 'agent identity from previous sessions', making the tool's function unambiguous. It also clarifies the scope by listing what is remembered (identity, ongoing work, learned knowledge). This clearly distinguishes it from siblings like 'remember' or 'recall' by framing it as a session-start restoration.

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 instructs to 'Call at the START of every session', providing clear when-to-use guidance. It does not mention alternatives or when-not-to-use, but the directive is strong enough to guide an agent.

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. It discloses a mutation operation ('create') but provides no details on side effects, required existence of memory IDs, relationship directionality, or whether existing relationships are replaced. This is a significant gap for a write 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 two sentences, front-loaded with the core action, and contains zero wasted words. Every part earns its place, though the trailing 'etc.' is slightly vague, but acceptable.

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?

While the tool is relatively simple and the schema is rich, the description lacks behavioral details such as return values, idempotency, or what happens on conflict. Given the absence of annotations and output schema, a bit more contextual disclosure would help, but it's not severely deficient.

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 all four parameters with descriptions (100% coverage), so the schema does the heavy lifting. The description adds no parameter-specific guidance, but the baseline of 3 is appropriate as the schema is sufficient.

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 ('create a relationship') and the resource ('between two memories'). It distinguishes itself from siblings like remember and recall by focusing on linking, not storing or retrieving. The additional 'build knowledge graphs' phrase reinforces its unique role.

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 usage context with concrete examples ('linking decisions to rationale, patterns to examples'), implying when to use this tool. However, it does not explicitly state when not to use it or offer alternatives to consider, so it lacks 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 burden. It clearly indicates a read-like operation ('Get') and specifies the content it loads, but does not mention potential side effects or prerequisites. Given the simple retrieval nature, it is sufficiently 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?

Two sentences, front-loaded with the action, every word earns its place. No unnecessary detail.

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 2 optional params and no output schema. The description explains the purpose, usage timing, and content. It is complete for a context-summary tool, though it does not mention return format, which is not critical here.

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 both parameters, so the baseline is 3. The description adds general context about what the summary includes (preferences, decisions, patterns), which helps interpret 'include_patterns', but does not add specific parameter semantics 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 tool 'Get a session context summary' with a specific verb and resource, and elaborates on the content (preferences, decisions, patterns). It implicitly distinguishes from sibling tools like 'remember' and 'recall' by focusing on session-level context rather than individual 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?

Explicitly says 'Call at the START of conversations', providing clear when-to-use guidance. However, it does not mention alternatives or when not to use the tool, so it falls 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?

No annotations are provided, so the description must disclose behavioral traits itself. It only hints at destructiveness with 'Use sparingly' but doesn't specify permanence, side effects, or how cascade affects removal. This leaves significant ambiguity for a mutation 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 extremely concise: two short sentences with no filler. It front-loads the core purpose and includes a behavioral warning, making every word earn 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, has full schema coverage, and no output schema, so the description doesn't need to explain return values. However, it lacks context on irreversibility, prerequisites, or the effect of cascade, making it minimally adequate 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?

Schema description coverage is 100% for both parameters (memory_id and cascade), and the description adds no extra parameter semantics. The baseline of 3 applies because the schema carries the necessary 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 clearly states the action ('Remove') and the resource ('a memory'), which is specific and differentiates it from siblings like remember (add) or recall (retrieve). It is a model of concise purpose 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?

The phrase 'Use sparingly' implies caution but does not explicitly state when to use this tool versus alternatives such as recall or connect. It gives a context of destructive action but lacks direct comparison or 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 must carry the burden of disclosing behavioral traits. It states the action and what data is saved, but does not explain side effects such as whether calling it multiple times overwrites previous state, or how it interacts with 'awaken.' For a state-saving tool, this lack of detail is a significant 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 two sentences, front-loaded with the core purpose, and every sentence contributes meaningful guidance. It is concise and well-structured, 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?

Given the tool's simplicity and high schema coverage, the description covers the essentials: what to do and when. However, it lacks information about return values or what happens after saving, and the absence of annotations means the behavior is not fully disclosed. It is adequate but with clear 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?

Schema description coverage is 100%, so the baseline is 3. The tool description adds some context by mapping parameters to session preservation (working_on, learnings, next_steps), but it does not provide syntax or examples beyond the schema. It adds marginal value.

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 function: 'Save current session state for next awakening.' It uses a specific verb (save) and resource (session state), distinguishing it from siblings like 'awaken' (which likely restores state) and 'remember' (which may deal with memories). It also specifies what is preserved: 'what you were working on, what you learned, and next steps.'

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 explicit timing: 'Call at the END of every session.' This provides clear usage context. However, it does not mention alternatives or exclusions (e.g., when not to use it), so it falls 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, the description carries the full burden. It uses the verb 'Browse', which implies a read-only operation, and explains what Intelligence Packs are. However, it doesn't explicitly state the return format or that it's a safe list operation, beyond the verb. This is adequate but not rich.

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 concise sentences. The first sentence front-loads the purpose, and the second adds useful context about what Intelligence Packs are, without unnecessary fluff. 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?

For a simple no-parameter list tool, the description provides sufficient context. It explains what the tool does and what the items are. It doesn't explicitly say it returns a list, but that is naturally implied. No output schema exists, so the description could have been more explicit about the return value, but the simplicity keeps this from being a major 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?

There are zero parameters, so the baseline is 4. The description doesn't need to add param info, and it doesn't. The schema has no properties, so the description correctly doesn't attempt to describe any.

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 with a specific verb ('Browse') and resource ('available Intelligence Packs (Specialist Hats)'). It distinguishes itself from the sibling tool 'wear_hat' by focusing on browsing rather than activation.

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 'Browse available' implies when to use this tool (to see what hats are available). While it doesn't explicitly name alternatives, the sibling 'wear_hat' serves a different function, so the context is clear. No explicit exclusions or when-not-to-use, but adequate.

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 transparency burden. It discloses the semantic matching behavior and the intended use case, but it does not state whether the operation is read-only, how results are returned, or any side effects, leaving some ambiguity.

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 short sentences with no fluff. The first two sentences deliver the core purpose, and the third gives a practical usage tip. It is front-loaded and 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?

The tool has no output schema and no annotations, yet the description is minimal. It gives a clear use case but omits any indication of what the search results look like and does not address edge cases. For a simple three-parameter search, this is borderline 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?

All three parameters are already fully described in the schema (100% coverage), so the baseline is 3. The description adds a little value by clarifying that 'query' is natural language ('by MEANING, not keywords'), but it does not elaborate on 'limit' or 'context' 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 'Search memories semantically' and 'Finds memories by MEANING, not keywords', specifying the action and resource. It distinguishes from sibling tools like 'remember' by emphasizing semantic retrieval, and adds a concrete usage context.

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 says 'Use at the start of sessions to restore context', providing a clear when-to-use scenario. However, it does not mention when not to use it or name alternative tools, so it lacks explicit exclusion guidance.

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 discloses the key behavior that memory persists across sessions, which is important. It does not elaborate on side effects, limits, or failure modes, but for a straightforward store operation this is sufficient; still, it lacks the depth seen in higher-scoring transparency descriptions.

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 concise sentences with no filler. The first sentence states the action, the second explains the use case. 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?

Given the tool's simplicity and the rich schema (all parameters documented), the description covers purpose and usage well. It doesn't mention return values, but there's no output schema and the operation is a straightforward store. However, it could mention the optional parameters to be more complete, so a 4 is fair.

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 all four parameters (content, context, metadata, importance) have descriptions. The tool description adds extra meaning by listing example content categories that map to the context parameter, but it doesn't add syntax or format details beyond the schema. Baseline 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 opens with 'Store a memory' – a specific verb+resource that clearly indicates the tool's write/persist function. It distinguishes from siblings like recall and forget by specifying it's for persisting information across sessions, and lists example memory types (decisions, preferences, architecture, patterns).

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 states 'Use this to persist decisions, preferences, architecture, patterns, or anything that should survive across sessions,' giving clear context on when to use it. However, it does not explicitly mention sibling tools like recall or forget as alternatives, so it earns a 4 rather than 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, the description carries the full burden of behavioral disclosure. It lists the specific types of statistics returned, which conveys what the tool outputs. However, it does not explicitly state that the operation is non-destructive or read-only, though 'Get' strongly implies this. The description adds meaningful detail about the nature of the returned data.

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 front-loads the action and lists the key outputs. Every word adds value, and there is no redundant or unnecessary information. This is an exemplary level of conciseness.

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?

Despite the absence of an output schema, the description enumerates the specific statistics returned, making the tool's behavior clear. Given the simplicity of the tool and zero parameters, this description is fully complete and self-contained.

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, and the schema is trivially complete (100% coverage). The description does not need to explain parameter semantics since there are none, and it appropriately focuses on the output. This matches the baseline score of 4 for tools with no 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 uses a specific verb ('Get') and resource ('memory statistics'), and enumerates the specific categories returned (total memories, relationships, vectors, patterns learned). This clearly distinguishes it from sibling tools like 'remember' and 'recall', which focus on individual memories rather than aggregate stats.

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 explains what the tool does but does not explicitly state when to use it versus alternatives, nor does it mention any exclusions or prerequisites. The context of 'memory statistics' implies it is for viewing overall memory health, but no direct guidance is provided, so the usage context is only implied.

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 discloses that it imports knowledge and layers personal memories on top, giving some behavioral context. However, it omits potential side effects, persistence, or whether activating a new pack replaces the previous one, leaving gaps in understanding.

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 succinct sentences, front-loaded with the primary action ('Activate') and resource. Every word adds value, and the metaphor of 'wear_hat' is clarified immediately.

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 one-parameter tool with no output schema, the description is fairly complete: it states the action, the effect on memory, and the layering behavior. It doesn't address deactivation or how this fits with sibling tools, but for its simplicity it covers the essential context well.

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 100% coverage with the parameter 'hat_id' described as 'ID of the Intelligence Pack to activate'. The tool description adds no new parameter-level detail beyond what the schema already states, so the baseline 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 clearly states the action ('Activate an Intelligence Pack') and the resource ('Intelligence Pack'), with a concrete effect ('Imports expert knowledge into your memory'). It distinguishes itself from sibling tools like 'remember' and 'recall' by focusing on pre-packaged knowledge rather than individual 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: use this tool to activate an Intelligence Pack for expert knowledge. It does not explicitly mention when not to use it or name alternatives, but the purpose is unambiguous, and siblings like 'list_hats' imply available options without needing explicit contrast.

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