Locul Cloud Memory

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

Annotations only tell the agent this is a non-read-only, non-destructive write; the description adds genuinely non-obvious behavior beyond that — deduplication ('If the same fact is already saved, nothing is added'), the immutability of existing records, and an explicit safety prohibition ('Never save secrets such as passwords or keys').

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?

Front-loaded with the purpose and usage trigger, then layers behavioral and content-quality rules. Every sentence carries a distinct rule, though the 'Creates a new record; it does not change or delete existing memories' clause partially overlaps with the dedup statement that follows.

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 6-parameter mutation with annotations but no output schema, the description covers purpose, trigger, non-destructive scope, dedup semantics, safety, and content-authoring guidance. It does not say what a successful call returns (e.g. whether an ID or the created record comes back), which is the main remaining 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 100%, so the baseline is 3, but the description goes further by telling the agent how to author the two semantically important fields: keep `fact` concrete and standalone, and populate `entities` with every person/company/product/project/tool/topic the memory touches. It adds no guidance on `kind`, `confidence`, `importance`, or `source_title` 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?

States a specific verb and resource ('Save one new memory to the user's Locul account') and immediately scopes it as additive ('Creates a new record; it does not change or delete existing memories'), which cleanly separates it from the read-oriented siblings like recall_memories, search, and get_entity_profile.

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 an explicit trigger condition: 'Use only when the user asks to remember or save something.' That is a clear when-to-use rule, but it never names the alternative tools (recall_memories, search) for the retrieval cases an agent might otherwise conflate with this one.

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 already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so 'Read-only' merely restates structured data rather than adding context. It says nothing about behavior for an invalid or missing id, output size, or truncation, so with annotations carrying the safety profile a 3 is appropriate.

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, zero filler, with the core action front-loaded and the qualifier placed after it. Every clause 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 one-parameter read tool with no output schema, the description covers what it returns (full text of a single memory) and how to source the id. It omits error behavior for an unknown id, but that is a minor gap for a simple read.

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 the schema already documents the single id parameter, but the description adds meaning beyond it by specifying the id's origin ('returned by search'), which tells the agent where to obtain a valid value. That is genuine added value over the schema's 'The memory id to fetch.'

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 (get) and resource (the full text of one saved memory) plus the scope/provenance of the key input. It also implicitly distinguishes itself from the sibling 'search', which returns ids rather than content.

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 'by the id returned by search' clearly frames this as the follow-up step after a search, so the agent knows the context. There is no explicit when-not use or naming of alternatives such as recall_memories, keeping it 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered and the trailing 'Read-only' is largely redundant. The description does add value by disclosing the shape of the result — aggregate counts and top-ranked entities — which annotations cannot convey.

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 well-structured sentence that front-loads the resource and what is returned. The trailing 'Read-only' fragment is redundant with the annotations and slightly dilutes the otherwise tight phrasing.

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 zero parameters and no output schema, the description carries the burden of hinting at return content, and it does so by naming counts and top entities. It omits ranking/ordering or time-window details, but for a simple aggregate read that is a minor 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?

The tool takes no parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-related guidance is needed or 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?

States a specific resource (the user's Locul account 'brain index') and enumerates what it covers: memory counts plus top people, projects, and topics. Clear verb+resource, but it does not distinguish itself from the sibling memory_stats, which plausibly overlaps in returning counts.

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 when-to-use guidance and no routing against alternatives such as memory_stats or get_entity_profile. The only directional hint is 'Read-only', which tells the agent nothing about when this overview is preferable to a stats or entity call.

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 already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so 'Read-only' is pure repetition of structured data and earns no credit. The remaining value is the sketch of returned content (key memories, related items, other names), but nothing is said about behavior when the entity is not found or when the name is ambiguous.

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 tight sentence with the entity types up front and the matching rule and read-only note trailing. Only the redundant 'Read-only' clause fails to earn its place against the annotations.

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, the description must carry return-value meaning, and it does gesture at the profile contents, which is adequate cover. However it omits miss/ambiguity behavior and any hint of the profile's structure or size, leaving meaningful gaps for a lookup 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?

Single parameter with 100% schema description coverage, so the baseline is 3. The description's 'match by name or key' duplicates the schema's own 'canonical key or name' wording, adding no matching rules, case sensitivity, or precedence between name and key.

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 specific verb and resource (show what is saved about a named entity) and enumerates the entity kinds it covers (person, company, product, project, tool, topic) plus the profile contents (key memories, related items, other names). It is clearly a single-entity profile lookup rather than a bulk search, but it never explicitly contrasts itself with siblings like search 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?

Only 'Match by name or key' is offered, which is invocation syntax rather than usage guidance. There is no statement of when to prefer this over search, recall_memories, or fetch, and no exclusions 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?

Annotations already declare readOnlyHint/destructiveHint, making the trailing 'Read-only' largely redundant. The valuable addition is the return-content description ('the memory plus the note's title and path'), which is real behavioral disclosure given there is no output schema.

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 compact sentence, front-loaded with the purpose and return content, with no filler. Every clause 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 single-param read tool with no output schema, the description covers both the operation and what comes back (memory + note title/path). Missing only minor details such as behavior when the memory id is unknown.

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?

Single parameter with 100% schema description coverage, so the schema already documents that id is a cloud uuid returned by recall/search. The description's 'by memory id' repeats this rather than extending it, so the baseline of 3 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 states a specific verb and resource ('show which note a memory came from') and names the keying parameter ('by memory id'), so an agent understands it's a provenance lookup. It doesn't explicitly distinguish itself from siblings like fetch or recall_memories, so it falls short of a 5.

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?

'By memory id' implies usage when a memory id is in hand, and the schema note 'as returned by recall/search' hints at the workflow, but there's no explicit when-to-use or when-to-prefer-a-sibling guidance. Adequate but implicit.

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 already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the trailing "Read-only." merely restates structured data and adds no credit. Nothing beyond that is disclosed about scope, permissions, or whether counts span all accounts or only the active one.

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 verb, with no wasted clauses. The second sentence is redundant with the readOnlyHint annotation, costing it the top 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 simple parameterless read tool, the description covers purpose adequately. However, with no output schema, it does not describe the return shape (e.g., a map of entity type to count), leaving the agent to guess what the response looks like.

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 takes zero parameters, so the baseline of 4 applies. There is no parameter surface for the description to clarify.

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 ("Count") and enumerates the resources counted (memories, people, projects, topics, source notes) within the user's account scope. This clearly distinguishes it from siblings like create_memory, search, and recall_memories, though it never names an alternative 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?

There is no guidance on when to use this tool versus search, recall_memories, or fetch. The counting nature implies an aggregate-stats use case, but no conditions, prerequisites, or exclusions are stated.

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 already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so "Read-only" merely restates structured data and adds no new behavioral information. Nothing is said about result ordering, pagination behavior, recency handling, or what an empty result means, leaving the behavioral picture thin for a retrieval 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?

Three short sentences with the core purpose front-loaded, then the optional filter, then the safety note. Almost every clause earns its place; only the trailing "Read-only." is redundant against the annotations.

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 three-parameter read tool with 100% schema coverage, full annotations and no output schema, the description covers what an agent needs to call it correctly. The one remaining gap — no hint about result volume, ordering or truncation behavior — is minor given the limit parameter is documented in the 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?

Schema description coverage is 100%, so the schema already documents query, entity and limit (with its default of 8). The description's entity sentence is essentially a paraphrase of the schema text and it says nothing about limit or query format, so it does not add meaning beyond the schema — the baseline 3 is correct.

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 (find/recall) and a clearly scoped resource ("the user's saved memories"), which separates it from generic siblings like search, search_notes, and fetch. However it never names or contrasts with those siblings, so an agent must infer the boundary between this and the plain search tool.

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 clear context for invocation — retrieval driven by "a question or topic" — and explains when to supply entity (to narrow to one person, company, project or topic). It stops short of any when-not guidance or explicit routing to alternative tools, so it is clear context without 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, and the trailing 'Read-only' merely restates them. Beyond that, the description discloses the id-based fetch handoff, which is genuine added value, but says nothing about result limits, ranking/matching behavior (semantic vs. keyword), or pagination.

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?

Three short sentences, front-loaded with the action and outcome, and the fetch guidance is placed where it is useful. The final 'Read-only' clause is redundant against the annotations and is the only wasted fragment.

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 read-only tool with no output schema, the description covers purpose, the return shape in rough terms, and the follow-up step. It still leaves an agent guessing about result count limits, ordering, and how this search differs from recall_memories, which matters given several overlapping siblings.

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 is a single parameter with 100% schema description coverage, so the baseline is 3. The description says the tool searches 'saved memories' but adds no detail about query syntax, matching mode, or scoping, so it does not exceed what the schema already provides.

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 ('Search the user's saved memories') plus the outcome ('return matching results'), which is clearer than a generic search. It does not, however, distinguish itself from sibling tools that clearly overlap in intent, notably search_notes and recall_memories, so an agent must infer the boundary.

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 one useful routing instruction — use fetch to retrieve full text of a result by id — which establishes the search-then-fetch workflow. It gives no guidance on when to prefer this over recall_memories or search_notes, and no exclusions, so usage is only partially 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?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the trailing 'Read-only' largely repeats it. The genuinely additive behavioral fact is that matching is keyword/exact rather than semantic, but return format, ordering and pagination behavior are unstated.

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?

Three short sentences with zero filler; the core purpose is front-loaded and the usage trigger and safety note follow in order of relevance. Nothing could be removed without losing signal.

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 two-parameter read tool with annotations carrying the safety profile, the description is adequate to invoke it. It is incomplete on the routing question (why this over 'search' or 'recall_memories') and gives no hint of what a result looks like or how it is ordered.

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% — 'query' (search terms) and 'limit' (max results, default 10, range 1-50) are fully documented in the schema. The description adds nothing about syntax, phrase handling, or case sensitivity, so baseline 3 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?

States a specific verb and resource ('Keyword search over the user's saved memories') and adds the mechanism (keyword/exact-match), which is more informative than the title. However, it never distinguishes itself from the closely named siblings 'search' and 'recall_memories', so the agent cannot fully disambiguate without inspecting schemas.

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?

'Use when the user gives exact words or names' gives a concrete, actionable trigger condition that separates keyword lookup from fuzzy/semantic recall. It stops short of naming the alternative tools (recall_memories, search) or stating when NOT to use it, so routing remains partly inferential.

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