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

Annotations provide readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description adds the concrete return shape (count/namespace/memories) and the migration workflow, which go beyond what annotations declare.

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 tight sentences; the purpose leads and the downstream workflow follows. Minor formatting oddity with the trailing markdown fence in the description text, but no wasted wording.

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 description covers purpose, output shape, and the migration handoff to import_memories, which is sufficient given there's no output schema and annotations cover safety. A note on large-vault size/pagination would complete it.

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?

Only one parameter with 100% schema coverage, where the schema already explains that "" means everything. The description reinforces the namespace scoping via the returned namespace field but adds little syntax detail; with full schema coverage a baseline of 3-4 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?

States a specific verb (export) and resource (memories) plus the output format (JSON-serializable dicts) and the use case (backup or migration). This distinguishes it from siblings like list_memories and memory_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?

Explicitly frames usage around backup or migration and names import_memories as the downstream tool, giving a clear when-to-use context. It doesn't state exclusions or contrast with list_memories/recall, 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?

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuine value beyond that: it stresses 'permanently' (irreversibility) and, since there is no output schema, describes the confirmation payload with id and a truncated preview.

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 destructive action front-loaded and the return behavior secondary. 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-parameter destructive tool with no output schema, the description covers the action, its permanence, and the shape of the return value. Only a note on error behavior for an unknown id is missing.

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 sole parameter memory_id is already fully documented in the schema, including its provenance. The description only restates 'by id' and adds no format, constraint, or edge-case detail beyond the schema baseline of 3.

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 with scope: 'Permanently delete one memory by id.' An agent can distinguish it from recall/list_memories/update_memory by the delete semantics. It does not explicitly name which sibling to prefer, 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?

The description never says when to forget a memory versus updating or exporting it, and offers no prerequisites or exclusions. The only routing hint (ids come from recall or list_memories) lives in the schema, not the description.

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?

Goes well beyond the annotations: validation-before-write, single-transaction atomicity ('a bad item changes nothing'), duplicate and expired-item skipping, field preservation and timestamp-to-UTC conversion, plus the exact return keys. This is exactly the behavioral detail annotations like idempotentHint and destructiveHint 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?

Front-loaded with the source relationship, then consequences, then return shape in three tight sentences. No filler; every clause carries actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter import tool with no output schema, the description supplies the return keys, the atomicity guarantee, and the dedup/expiry behavior. Combined with the annotations, an agent has everything needed to invoke and interpret it.

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% but the schema itself is nearly opaque (an array of objects with additionalProperties). The description compensates by specifying the required non-empty 'content' field and which optional fields are preserved, adding real meaning beyond the schema. It could still clarify the accepted timestamp formats more concretely.

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+resource ('Import memories') and ties the input source directly to the sibling tool export_memories, so an agent can immediately distinguish this from remember/update_memory and knows where the payload originates.

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 frames the use case as restoring data from a prior export_memories call, which is clear context. It stops short of stating when-not to use it (e.g., for single ad-hoc additions, use remember instead), leaving that routing to inference.

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 and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by describing the return shape and the conditional expires_at field, though it says nothing about pagination or how to retrieve beyond the limit.

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 tight sentences with no filler; the scoping constraint is front-loaded and the return-shape note follows immediately. 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?

With no output schema, the description usefully compensates by stating the return keys and the conditional expires_at. Annotations cover safety, and params are fully documented. Only pagination behavior for the default limit of 20 is left unaddressed.

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 tag, limit, and namespace are fully documented in the schema with defaults and empty-string semantics. The description adds no parameter-level detail beyond the schema, so the 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 ('Browse stored memories') with ordering ('most recent first') and a scoping constraint ('without a search query'). This implicitly separates it from recall/search-style siblings, though it never names them.

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 'without a search query' makes the usage context clear — this is the browsing path when no query exists, as opposed to a search/recall path. No explicit alternative is named, so it falls short of a full 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 and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses the diagnostic nature of the output and surfaces the internal search_mode fallback ('fts5' vs 'like'), which is unusual and useful context.

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 purpose sentence is front-loaded and efficient. The follow-up enumeration is long but each item earns its place since there is no output schema to describe the return shape; a minor redundancy exists between 'statistics and health information' and the explicit field 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?

With no output schema, the description fully carries the burden of describing the return payload: totals, per-namespace counts, top tags, active-TTL count, db size and path, schema_version, and search_mode with its enum values. An agent knows exactly what it will get back.

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 is 4. The description correctly implies no inputs are needed; there is nothing further to document.

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 pair ('Get vault statistics and health information') and immediately enumerates the scope of what is returned. It is clearly distinguishable from recall/remember/forget by topic, but it never explicitly contrasts itself with any sibling.

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. The parenthetical '(handy to pick tags consistently)' hints at one diagnostic use case, and the 'health information' framing implies introspection, but there is no explicit when-to-use, when-not, or alternative tool 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?

Annotations already declare readOnlyHint and openWorldHint, yet the description goes well beyond them: it discloses the ranking algorithm (SQLite FTS5 bm25 with recency tiebreaker), the auto-match fallback behavior, the 'note' emitted on partial matches, and the 'hint' on empty results. That is genuine behavioral context an agent would otherwise have to discover by trial.

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 search behavior is front-loaded and the return-shape paragraph is dense but skimmable. The sentence enumerating every hit field is somewhat list-like, but no sentence is redundant given the absence of an output schema.

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 carries the return contract and does so fully: the top-level envelope keys, per-hit fields, snippet bracketing, the note flag and the hint. Combined with annotations, an agent has everything needed to invoke and interpret recall.

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 baseline is 3, but the description adds real meaning on top: it clarifies that plain questions work, that terms match by prefix, and that match='auto' falls back from all to any with an accompanying note. These reinforce and extend the enum and query 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?

States a specific verb and resource ('Search memories by full text') plus a scope promise ('best matches first'). It contrasts implicitly with list_memories by emphasizing relevance ranking and full-text matching, but never names a sibling to sharpen 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?

Explains what happens with punctuatation, filler words and prefix matching, and describes the default match='auto' fallback chain, which tells the agent how the search behaves. However, it never states when to reach for recall versus list_memories or memory_stats, 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?

Annotations already declare idempotentHint=true and destructiveHint=false; the description adds genuinely new behavior: exact duplicates in the same namespace are never double-stored, the existing memory is returned with deduplicated=true, new tags are merged and reported in merged_tags, and tags are case-insensitive. This is exactly the extra context annotations cannot carry, and it is consistent with them.

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 core action, then trigger guidance, then edge-case semantics, then return shape. Every sentence earns its place, though the return-value paragraph is slightly verbose given it repeats field names that the caller can discover at runtime.

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?

There is no output schema, so the description correctly takes on the burden of describing the response (id, content, namespace, tags, timestamps, deduplicated, merged_tags, message). Combined with dedup, namespace scoping, and tag case rules, an agent has everything needed to call and interpret this write tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: dedup is scoped to 'same content in the same namespace' (clarifying namespace semantics) and tags are case-insensitive with merge behavior on duplicates. No syntax or format gaps remain.

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: 'Store a fact in persistent memory', with the scope qualifier 'so it survives across sessions'. It is clearly distinguishable from retrieval siblings like recall in spirit, but it never names an alternative explicitly, so it stops 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?

'Use this whenever you learn something worth keeping' plus concrete examples (user preferences, project decisions, environment quirks, follow-ups) gives a clear trigger. It omits any when-not guidance or named alternative (update_memory, forget), which keeps it out of 5 territory.

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 it as non-read-only, destructive, idempotent, and closed-world. The description adds meaningful behavioral detail beyond that: duplicate detection with a named error, and the return shape including 'updated_fields'.

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-loads the core edit operation in the first sentence, then adds usage guidance, duplicate-refusal behavior, and return information without filler. 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 mutation tool with no output schema and a rich annotated profile, the description covers the essential missing pieces: when to prefer it over creating a duplicate, duplicate-refusal behavior, and the return shape. Parameter behavior is fully covered by the schema, so nothing critical is absent.

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 all seven parameters are fully documented in the input schema. The description only lists field names (content, tags, namespace, source, TTL) that the schema already defines, adding no extra syntax or constraints.

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 ('Edit') and resource ('existing memory'), enumerating mutable fields. The sentence about preferring it over storing a second memory distinguishes it from the create-oriented sibling 'remember'.

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 a clear use case—when a fact changes and a second contradicting memory would otherwise be stored—and names the alternative behavior. It lacks explicit when-not guidance, but the condition for choosing this tool is clear.

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