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 implies a read-only filter but never confirms it, and says nothing about how results are selected or ranked, whether an empty result is possible, or what happens when filters are omitted (all defaults are null/optional).

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 tight sentence with no filler and the filtering criteria front-loaded. It is efficient but borders on under-specification for a five-parameter curation 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?

An output schema exists, so return-value explanation is not required. Still, for a 5-parameter, zero-required, annotation-free tool, the description does not convey the curation/selection behavior (how many picks, how they are chosen) that distinguishes it from a plain watchlist lookup.

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 all five parameters including defaults and examples. The description's mention of time, genre, and IMDb rating adds nothing beyond the schema and leaves media_type and count unmentioned; 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?

States a clear verb (filter) and resource (watchlist) plus three filtering criteria, so an agent can tell it produces a narrowed list. However, it never differentiates itself from siblings like get_watchlist or search_media, and it omits two of its own parameters (media_type, count), leaving the 'curated subset' angle unexplained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus get_watchlist (unfiltered list) or get_agent_recommendation_brief / vet_recommendation_candidate. The 'tonight' intent in the name suggests a time-boxed personalized pick, but the description never states that condition or any exclusion.

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 supplied, so the description carries the full behavioral burden, yet it only says a pairing is 'generated'. It does not disclose whether the operation is read-only or writes anything, whether it depends on stored taste/vault data, whether results are deterministic, or that the result is AI-generated rather than indexed. Significant behavioral gaps for a tool with zero annotation coverage.

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 front-loaded sentence with no filler; the core purpose is stated immediately. It is arguably too terse for the amount of behavior it omits, but there is no wasted text.

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, and the schema fully documents inputs. However, with no annotations and no usage or behavioral detail, the definition is only minimally sufficient for a generative cross-domain tool that presumably relies on stored data from sibling logging tools.

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 four parameters (mood, anchor_type, title_or_name, author_or_creator) are documented in the schema itself, including examples and allowed values. The description adds no parameter meaning beyond that, which matches the baseline of 3 when the schema does the heavy lifting.

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 ('Generate') and a concrete resource ('aesthetic cross-domain pairing connecting books/movies with sensory beverages'), which is enough for an agent to know what the tool produces. It does not need sibling differentiation since no other tool in the list performs cross-domain pairing, though it stops short of describing the shape of the pairing itself.

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 when-to-use guidance, no mention of prerequisites (e.g. a logged sensory item or vault entry), and names no alternatives such as curate_for_tonight or get_agent_recommendation_brief. The agent must infer the trigger context entirely.

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 disclosure burden. 'Retrieve' weakly implies a read, but nothing states permissions, whether it triggers external web search, cost/latency, or caching behavior. The listed return contents overlap with the output schema rather than adding behavioral 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?

A single front-loaded sentence with no filler. Slight redundancy in enumerating payload fields that the output schema already carries, but no wasted prose.

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?

Because an output schema exists, return values need no explanation, and all three parameters are schema-documented. Still, for a tool sitting in a dense sibling cluster, the absence of any positioning or usage cue leaves the definition only minimally 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?

Schema description coverage is 100% and each parameter is clearly documented, so the baseline is 3. The description only gestures at 'domain' and says nothing about how mood_or_intent or target_location shape the brief.

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?

Specific verb 'Retrieve' plus an enumerated payload ('Taste DNA, anchor favorites, avoidances, and web search queries') makes the purpose concrete. It does not, however, distinguish itself from the closely related sibling get_user_taste_profile, so an agent must infer the split.

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, when-not-to-use, or alternative routing is given. With 19 siblings including get_user_taste_profile and vet_recommendation_candidate, the definition offers nothing to help pick between them.

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. 'Get ... statistics' implies a non-mutating read, and the enumeration of covered domains is useful context, but there is no disclosure of scope limits, refresh behavior, permissions, or whether the aggregation is global or user-scoped.

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 front-loaded sentence with no filler or redundant restatement of the title. Every clause (verb, resource, domain list) 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?

A zero-param read tool with an output schema needs little prose, and the description does state the full breadth of aggregated domains. The only gap is the absence of any guidance on when to prefer this over the per-domain sibling tools.

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 there is nothing for the description to disambiguate; the 4 baseline applies. The schema is empty and fully consistent with the description's no-argument framing.

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 ('macro statistics') and enumerates the six domains it aggregates, which separates it from the per-domain search/log siblings. It doesn't explicitly name an alternative such as get_user_taste_profile, so it falls short of full sibling differentiation.

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 word 'macro' plus the multi-domain scope signals a high-level summary view rather than per-item lookups. No when-to-use condition or named alternative is given, so the agent must infer the routing decision.

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 behavioral burden. It does not state that this is a read-only operation, whether authentication/account scoping is required, or how pagination/limit behaves beyond the default. Only the queue values are disclosed.

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 tight sentence with zero filler, and the resource plus valid queue values are front-loaded. Nothing needs trimming.

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, and both parameters are fully documented in the schema. However, with no annotations the description should still cover the read-only nature and scope, which it omits, leaving it only minimally viable.

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 both parameters (limit, shelf) are already fully documented in the schema. The description merely repeats the shelf values with no added syntax, format, or behavioral meaning, 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?

The description states a specific verb (get) and resource (books from the user's reading queue) and enumerates the two valid queue values. It implicitly separates itself from search_books and get_watchlist, but never names a sibling to sharpen the distinction.

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 this is for fetching the user's own queued books rather than searching. There is no guidance on when to prefer this over search_books, nor any 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?

With no annotations, the description carries the full disclosure burden, but 'Retrieve' does convey a read-only, non-mutating operation. It adds no information about permissions, data source, or freshness/scope, though the return-shape burden is partly lifted by the existing 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?

A single front-loaded sentence with no filler; the verb and resource come first and the content list follows economically.

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 zero-parameter read tool with an output schema already documenting the return payload, the description is nearly sufficient. The only gap is sibling differentiation, which the description does not address.

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 there is nothing for the description to disambiguate; the structural baseline of 4 applies. No parameter-level detail is expected 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?

The description states a specific verb ('Retrieve') and resource ('user taste profile') and enumerates the contents (top genres, directors, authors, highest-rated favorites). It is clear on its own, but it does not distinguish itself from adjacent siblings like get_entertainment_stats or get_agent_recommendation_brief, leaving the agent to guess which profile-style tool to pick.

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 call this versus the other profile/stats/recommendation siblings, and no prerequisites or exclusions are given. The agent must infer usage purely from the tool name.

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. 'Get' implies a non-mutating read and the output schema covers return shape, but nothing is said about empty-watchlist behavior, ordering, or pagination, leaving some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single efficient sentence with the core action front-loaded and the filter modifiers trailing. Nothing is wasted, though it is quite terse relative to the guidance it omits.

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 read-only getter with an output schema covering return values and fully documented parameters, the description is adequate. The only real gap is the absence of routing guidance against the many sibling retrieval tools.

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 three parameters are already documented in the schema. The description mentions the type and genre filters but adds no syntax or value guidance beyond that, and omits the limit parameter entirely. Baseline 3 applies when the schema does the heavy lifting.

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 (movie and TV watchlist), and notes the filter dimensions. It is clear on its own but does not distinguish itself from siblings like search_media or get_reading_list, so sibling routing is left to inference.

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 explicit when-to-use or when-not-to-use guidance and no named alternative. 'Optional type and genre filter' hints at usage but never states when an agent should pick this over search_media or curate_for_tonight.

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

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

No annotations provided, so the description carries full disclosure burden. It implies a write operation but does not state side effects, whether duplicates are created, auth requirements, or what happens when book_id is omitted vs provided. The presence of book_id and multiple optional note fields (notes, review, private_notes) raises behavioral questions the description doesn't address.

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?

Single efficient sentence that front-loads the action and key fields. No waste, appropriately sized for a straightforward logging 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 described. However, with 8 parameters, no annotations, and an overlapping trio of text fields (notes/review/private_notes), the description is incomplete for an agent to call this correctly — it should clarify field intent and whether book_id resolution creates or links records.

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 parameters are documented in the schema. The description adds meaning by clarifying rating scale (0-5 stars) and that review is optional, but doesn't explain the distinction between notes, review, and private_notes — a real ambiguity given three overlapping text fields.

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?

Clear verb (Log) and resource (completed book) with key fields named (rating, review, date). Distinguishes from read-oriented siblings like search_books and get_reading_list by being a write/log tool. Lacks explicit sibling differentiation but the verb itself separates it well.

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, no mention of the sibling log_watched_media, log_restaurant, log_sensory_item which follow the same logging pattern. No exclusions or prerequisites stated. The agent must infer this is for finished books only.

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, yet it says nothing beyond the purpose sentence. It does not disclose that this is a write/create operation, whether it is idempotent, how an existing entry is handled if 'name'/'restaurant_id' collides, or what happens when only the three required fields are supplied.

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, front-loaded sentence with no filler or redundancy. It is efficient, though arguably too terse for a 14-parameter mutation tool, which is a completeness problem rather than a conciseness one.

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 14-parameter write tool with zero annotations, no usage routing, and no stated side effects, one sentence is thin. The presence of an output schema removes the need to describe return values, but the description still leaves the agent without enough to know when and how safely to call 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 description coverage is 100%, so each of the 14 parameters is already documented with examples and defaults; the baseline is 3. The description's 'dining journal or wishlist' phrasing loosely signals the visited/wishlist distinction but adds no format, default, or constraint detail 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 gives a specific verb ('Log') and resource ('restaurant or dining experience') and even names the two destination buckets (dining journal vs. wishlist), which maps onto the status parameter. It is clear enough to distinguish from read-side siblings like search_restaurants, though it never names them 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 choose this tool over search_restaurants, get_agent_recommendation_brief, or vet_recommendation_candidate, and no mention of prerequisites such as needing an existing recommendation. The journal-vs-wishlist phrasing implies usage but states no conditions 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 carries the full burden. It says 'log or update' (a mutation) but never states whether an update overwrites prior fields, merges them, requires ownership, or is reversible. For a 14-parameter write tool with zero annotation coverage, this is a significant disclosure 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?

A single sentence with the verb and resource front-loaded and the domain list appended for disambiguation. Nothing is wasted and nothing needs to be scanned past.

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, but for a 14-parameter mutation tool with no annotations, the description omits create-vs-update semantics, overwrite behavior, and routing to search_sensory_vault. It is too thin for the tool's complexity.

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 14 parameters are already documented, making 3 the baseline. The description only repeats a subset of the category values ('tea, whiskey, coffee, wine, gin, perfume, watch') and actually omits 'chocolate', which the schema lists, so it adds no reliable meaning 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 pair ('log or update') and resource ('item in the Sensory Vault'), and enumerates the domains it handles, which separates it from log_read_book, log_watched_media, and log_restaurant. It does not explicitly name search_sensory_vault as the read-side alternative, so sibling differentiation is implied 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?

The phrase 'log or update' hints at two modes but never explains when to use which, nor when to reach for search_sensory_vault instead. No prerequisites, no mention that item_id selects update vs create. The agent must infer usage entirely from the schema.

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 behavioral burden, yet it discloses nothing beyond the write intent. It does not say whether logging creates or updates an entry, how duplicates/IDs are resolved, what permissions are needed, or what happens when a title matches nothing in the library.

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 front-loaded sentence with zero filler — the core action comes first. It is tight, though it omits useful detail rather than being over-long, so it is efficient without being exemplary.

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 an eight-parameter mutation tool with no annotations, the description is too thin: it ignores media_type (movie vs tv), the optional imdb_id/tmdb_id/year matching fields, and default behaviors like date_watched defaulting to today. An output schema exists, so return values needn't be explained, but input and side-effect behavior remain under-specified.

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 all eight parameters, including the 1-10 rating range, media_type values, and ISO date format. The description merely restates rating/review/date, adding no syntax or format meaning beyond the schema, which makes the 3 baseline 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 (log) plus the resource it applies to ('watched movie or episode'), and the media scope implicitly separates it from siblings like log_read_book or log_restaurant. It never names an alternative tool or explicitly contrasts with siblings, 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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named despite relevant siblings (search_media, get_watchlist, vet_recommendation_candidate). Usage is only inferable from the verb 'log watched'.

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 behavioral burden. 'Recall' implies a safe read, but the description never confirms read-only/non-destructive behavior, permissions, or any traits beyond the bare action.

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 front-loaded sentence with no filler or redundancy. It is efficient, though its brevity borders on under-specification rather than tightness.

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, and all four parameters are optional and fully documented in the schema. However, for a tool with zero annotations, the description leaves usage context and behavioral expectations 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 the baseline is 3. The phrase 'topic or category' loosely maps to query and category, but adds no syntax, examples, or default behavior beyond what the schema already documents.

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 (recall) and resource (stored memories and directives) with the filtering dimension (topic or category). It is distinguishable from the obvious sibling store_memory by direction, but does not differentiate itself from other retrieval tools like search_vault.

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 when-to-use guidance, no prerequisites, and no mention of alternatives. An agent gets no signal about when recall is preferred over search_vault or the other retrieval siblings.

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

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

No annotations are provided, so the description carries the full burden. It notes the backing store (Firestore) but never states that this is a read-only operation, nor describes matching behavior, result ordering, or pagination. For an unannotated tool this is a notable disclosure 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?

A single front-loaded sentence that names the resource, the primary matcher, and the optional filter with zero filler. It could earn a 5 only by adding a differentiating clause, but it is efficiently sized.

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, and all parameters are documented. What is missing is the usage context (when to pick this over sibling search/list tools), leaving the definition minimally viable rather than 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?

Schema description coverage is 100%, with each of the three parameters already documented (limit default, query match against title/author, shelf enum values). The description repeats the query and shelf semantics without adding format or edge-case detail, 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 (search) and resource (books) plus the matching mechanism (query) and the shelf filter. It is clear what the tool does, though it does not distinguish itself from siblings like get_reading_list or log_read_book, which an agent might confuse for book-related operations.

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 only restates the optional shelf values with no when-to-use guidance, no mention of when to prefer search_books over get_reading_list or search_vault, and no prerequisites. An agent must infer the retrieval-vs-list distinction on its own.

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 behavioral burden and it discloses almost nothing. It does not explain matching semantics (substring vs exact), what happens with the default empty query, sort order, or whether the search spans the user's whole library. It only repeats the read-style verb 'search'.

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 front-loaded sentence with no filler. It is efficient, though arguably too terse for a 4-parameter search tool where routing and matching behavior matter.

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 described, and the annotations are absent while all four parameters are documented in the schema. What is missing is behavioral and routing context: default-empty-query behavior and how it relates to sibling discovery tools.

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 description does add value by clarifying what the vague 'Search keywords' query matches against (title, director, genre), but it ignores the status and media_type filters entirely.

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 ('Search') and resource ('movies and series in library') and names the searchable facets (title, director, genre). The media scope implicitly distinguishes it from search_books, search_restaurants and search_sensory_vault, but 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?

There is no when-to-use or when-not-to-use guidance. With several overlapping siblings (get_watchlist, vet_recommendation_candidate, curate_for_tonight), the description never explains when to run a raw library search instead of those alternatives.

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

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing beyond the facets already in the schema. It does not state that the operation is read-only, how filters combine, how an empty query behaves, or what result ordering/limits apply.

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 front-loaded sentence naming the action and the facet set, with no filler or 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?

With 7 optional parameters, full schema coverage, and an output schema that handles return values, the one-line description is minimally adequate. It still omits how the filters combine and confirms nothing about the default empty query, which an agent would benefit from knowing.

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 every parameter (city, vibe, limit, query, status, cuisine, min_rating) is already documented in the schema. The description only restates a subset of those facets and adds no format or interaction details, 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 (Search) and resource (dining vault) and enumerates the filter facets (keyword, city, cuisine, status, vibe tag), so the agent knows exactly what it retrieves. It does not, however, differentiate itself from sibling search tools like search_vault or search_sensory_vault.

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 when-to-use or when-not-to-use guidance and no mention of alternatives, even though several sibling search_* tools exist. Usage is only implied by the resource name.

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 behavioral burden. 'Search' implies a read, but the description says nothing about result ordering, pagination behavior, empty-result handling, or whether filters are ANDed together — all meaningful for a 6-parameter query 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?

A single tight sentence with the verb and resource front-loaded and no wasted words. It is perhaps too terse given the tool's complexity, but nothing is padded.

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 schema covers all parameters. Still, for a six-parameter cross-category search with no annotations and an overlapping sibling (search_vault), the description leaves routing, filter combination, and result behavior unspecified.

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 all six parameters with examples. The description's facet list (keyword, category, rating, flavor tag) partially mirrors the schema but omits the status and limit filters, adding no syntax or semantics beyond it.

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 ('Search') and resource ('sensory vault items') and enumerates the supported filter facets. However, it does not distinguish this tool from the sibling search_vault (or search_books/search_media/search_restaurants), leaving the agent to guess which vault to query.

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 facet list hints at supported filters but gives no when-to-use guidance, no indication of when search_vault is the better pick, and no prerequisites or exclusions. The agent is left to infer routing on its own.

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 behavioral burden, and it discloses almost nothing: no mention of how results across domains are combined or ranked, no pagination behavior, and no read-only/reversibility framing beyond the implied meaning of 'search'. For a cross-domain aggregator with five underlying domains, this is a real 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?

A single front-loaded sentence with no filler; the scope and covered domains are stated immediately. 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?

An output schema exists and schema coverage is complete, so return values and parameters need not be re-explained. What is missing is the piece only prose can supply: guidance on choosing this unified search over the four overlapping domain-specific search siblings. Adequate but with a clear routing 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%, with all three parameters (query, limit, domain) documented in the schema itself. The description's parenthetical domain list loosely maps to the 'domain' values but adds no syntax, matching, or format detail beyond what the schema already supplies, 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 ('Unified search across all collections') and enumerates the covered domains, so an agent knows this spans books, media, sensory goods, restaurants and quotes. It implicitly contrasts with the domain-specific siblings but never names them, so the differentiation is inferable rather than explicit.

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?

'Unified across all collections' implies this is the cross-domain entry point, which is useful given siblings like search_books, search_media, search_sensory_vault and search_restaurants. However, it never states when to prefer this over a domain-specific search or how to scope results, leaving the routing decision 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?

No annotations are provided, so the description carries the full behavioral burden. It does not explain persistence semantics, whether duplicate memories are merged, what happens on retrieval, or any permissions or side effects. Only the base action is stated, leaving significant gaps for a mutation-style 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 a single, front-loaded sentence with no filler. It is efficient, though its extreme brevity pushes against the informational needs of the tool rather than being a structural flaw.

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 a four-parameter mutation tool with no annotations and an output schema that handles return values, the description is too thin. It omits routing guidance relative to recall_memories, behavioral details about long-term storage, and any indication of scope or deduplication, leaving an agent under-informed for correct 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?

Schema description coverage is 100%, so the schema already documents all four parameters in detail. The description adds a loose content-type list that partially overlaps with the category values, but provides no additional syntax, constraints, or examples beyond what the schema already gives. A 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 states a specific verb ('Store') and resource ('long-term memory'), and enumerates the kinds of content accepted (preference, habit, directive, constraint). This clearly distinguishes it from the retrieval-oriented sibling recall_memories, though it does not name that sibling 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 alternatives such as recall_memories or the many domain-specific logging/search tools. The description merely states what it does; an agent must infer the appropriate context from the tool name alone.

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 of behavioral disclosure. It states two operations (collision check and affinity scoring) but says nothing about side effects, permissions required, what happens on collision, or whether the operation is read-only.

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 sentence with no wasted words. The compound purpose is front-loaded and immediately scannable.

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 tool with four parameters and no annotations, the description is too thin. While the output schema covers return values, the description lacks usage guidance, behavioral details, and any indication of how collision results or affinity scores should be interpreted.

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 four parameters are documented in the input schema. The description adds no additional meaning about parameter usage, formats, or constraints beyond what the schema already provides, making the baseline score of 3 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 states a clear compound purpose: check a recommendation candidate for library collision and calculate a taste affinity score. It identifies the resource (recommendation candidate) and the specific actions, but does not differentiate this tool from sibling tools like search_vault or get_user_taste_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?

There is no explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The context of 'recommendation candidate' implies a vetting step, but the agent must infer this and receives no routing instructions.

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