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

With no annotations, the description carries the full burden. It usefully discloses irreversibility ('permanently delete'), which is the key trait for a destructive tool, but says nothing about confirmation requirements, permissions, or behavior on an invalid/nonexistent memory_id.

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?

One short sentence, front-loaded with the action and irreversibility, with the example parenthetically appended. No 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?

An output schema exists, so return values needn't be described. For a one-parameter destructive tool, the main missing piece is how to source the memory_id and any confirmation/error semantics.

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 0% and the description never mentions memory_id, so it adds no meaning about the identifier's format or where to obtain it (recall/list_memories). The single parameter is self-explanatory by name, preventing a lower 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?

States a specific verb and resource: 'Permanently delete one memory.' The word 'one' distinguishes it from bulk/list siblings like list_memories, though no sibling is named explicitly.

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?

Gives one triggering example ('when the user asks to be forgotten'), which clarifies intent, but offers no conditions for when not to use it or which sibling to use instead (e.g., recall to find the ID first).

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 behavioral burden. It helpfully discloses that results include mention counts per entity, but it omits pagination, result limits, sorting, and authentication/scoping 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, waste-free sentence that front-loads the entity categories. It is efficient, though it does not lead with an explicit verb like 'List'.

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?

An output schema exists, so return values need not be explained. For a simple one-parameter list tool, the description covers the resource adequately, but gaps in usage guidance and user_id semantics keep it from being fully 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?

The sole parameter user_id has 0% schema description coverage, so the description should compensate. It implies user scoping via 'the user's memory' but never mentions the parameter, its default, or accepted format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource precisely: people, pets, places, and organizations in the user's memory, plus mention counts. It is clear what the tool enumerates, but it does not explicitly distinguish itself from siblings like list_memories or 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?

There is no guidance on when to use this tool versus siblings such as list_memories, recall, or remember. The retrieval context is implied by 'user's memory,' but no alternatives or exclusions are named.

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 disclosure burden. It usefully states the default behavioral trait that only current facts are returned unless include_history is true, but it does not mention read-only status, permissions, pagination, or other 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, front-loaded sentence with zero wasted words. It efficiently conveys the core resource and the key default scope caveat.

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 two parameters and an output schema, so the description needn't explain return values. Still, it leaves gaps around user_id semantics and when to choose this tool versus recall, which are relevant given the sibling-tool context and zero schema description coverage.

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 clarifies the meaning of include_history and the default current-facts behavior, but it does not explain user_id beyond the phrase 'about a user,' leaving the identifier semantics only partially 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 that the tool returns everything remembered about a user, with a default current-facts-only scope. It does not explicitly distinguish itself from sibling tools like recall, but the purpose is specific enough for an agent to understand the resource being listed.

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 when to use the tool by saying it returns everything remembered about a user, and it explains that history is included only when include_history is true. However, it gives no explicit guidance about when to prefer this over siblings such as recall or list_entities.

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 behavioral burden. It usefully discloses that each result indicates whether it is current or no longer true, but it omits other behavioral context such as read-only nature, permissions, or result limits.

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 short sentences, front-loaded with the core purpose and no wasted wording. The description is appropriately sized for the tool.

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?

Output schema exists, so return values need not be explained, but with no annotations and 0% schema coverage the description leaves key gaps. It does not address sibling alternatives, parameter meanings, or user scoping.

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, but it does not. It only implies the query parameter and leaves k and user_id unexplained, including their defaults and scoping role.

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 and resource: "Find memories relevant to a query." It is clear what the tool does, but it does not explicitly distinguish itself from siblings like list_memories or list_entities.

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 this tool versus alternatives such as list_memories, remember, or forget. It implies retrieval use but provides no exclusions or decision criteria.

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, and it does disclose a genuinely non-obvious behavior: superseded facts (new city, new job) are recorded as updates and the old value is retained as history, so nothing is destructively overwritten. It omits other behavioral context such as per-user scoping or duplicate handling, but the key mutation semantics are covered.

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, zero waste, with the core action front-loaded and the update/history caveat following immediately. Nothing is repeated from the name or title.

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?

An output schema exists, so return values need no explanation, and the tool is a simple two-parameter write. However, the unexplained user_id scoping and the absence of any routing guidance against forget/recall leave gaps for an agent operating in a memory-tool cluster.

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 and largely doesn't. It never explains what 'text' should contain (a sentence? a fact tuple?) nor what 'user_id' scopes, even though its 'default' value implies multi-user partitioning that an agent could easily get wrong.

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?

States a specific verb (store) and a specific resource (facts the user shares about themselves), which clearly separates it from retrieval siblings like recall and list_memories. It stops short of naming any sibling explicitly, so differentiation is inferred from the verb rather than stated.

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?

Usage is only implied: an agent can infer it should call this when the user reveals personal facts, but there is no explicit 'use when' framing, no guidance on when to prefer forget or recall, and no mention of how this interacts with list_entities/list_memories.

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