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

With no annotations, the description carries the full burden. It discloses the anti-hallucination framing and that passages are the sole context, but it fails to clarify whether retrieval happens internally (params like alpha, top_k, source suggest it does) despite claiming to use 'reranked passages'. Key behavioral facts such as this are left implicit.

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 the core purpose front-loaded and no filler. Efficient, though not especially rich.

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 helper's role is conveyed. But with 7 undocumented parameters and no annotations, the description is thin for a tool this configurable.

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

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

Schema description coverage is 0% across 7 parameters, so the description must compensate and does not. 'Reranked' vaguely gestures at the ranking parameters (alpha, top_k) but none of source, text_filter, metadata_filter, or context_limit_chars are explained.

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

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

The description uses a specific verb+resource ('Build a RAG prompt using the reranked passages') and specifies the output ('a cited context and a ready-to-send prompt'). This lets an agent distinguish it from retrieval siblings like search. However, the name says 'generate_rag_answer' while the description says it only builds a prompt, a minor mismatch, and no sibling is explicitly named.

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

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

It hints that the tool consumes 'reranked passages' as the only context, but gives no explicit when-to-use guidance or alternatives. There is no statement on how it relates to the search siblings or when an agent should reach for it versus plain search.

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

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

No annotations are provided, so the description carries the full burden. It discloses only the payload topic ('statistics about indexed documents and chunks') and says nothing about read-only safety, cost, latency, or behavior when the collection is empty or not yet indexed.

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 purpose. The 'Returns:' line is largely redundant given an output schema exists, but the overall size is appropriate and there is no padding.

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?

This is a zero-parameter read tool with an output schema, so the description does not need to enumerate return fields or arguments. It adequately covers purpose, though it never positions itself against the search/metadata 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description adds nothing here, but there is nothing to add.

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: 'Get statistics about the indexed document collection.' An agent knows what it retrieves, but the description never distinguishes it from adjacent siblings like get_metadata or list_papers, so the scope boundary 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 when-to-use guidance, no prerequisites, and no mention of alternatives. The description only says what it returns, so an agent has to guess whether this or get_metadata is the right call for a collection-level question.

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. 'Get' implies a read operation, but it says nothing about permissions, rate limits, or what 'complete' encompasses. It provides no behavioral context beyond the ambiguous word 'complete.'

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 no waste, and the resource is front-loaded. It is arguably too terse for the information an agent needs, but structurally sound.

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 existence of an output schema means return values need not be described, which covers the biggest potential gap. However, for a lookup tool among many search siblings, the description should say more about when this is the right call versus searching.

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% with a single documented doc_id parameter, so the schema does the heavy lifting. The description adds nothing about identifier format or where it comes from, which is the correct baseline when the schema is complete.

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 (metadata) scoped to 'a specific paper,' so the agent knows it is a targeted lookup rather than a search. It does not differentiate itself from siblings like search or list_papers, which is a missed opportunity given nine siblings.

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 guidance, no prerequisites, and no mention of alternatives such as search or list_papers. Usage is only implied by the word 'specific,' leaving the agent to infer that a known doc_id is required.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It usefully describes incremental processing, chunking, deduplication, and progress tracking, but omits key operational traits such as whether it mutates a persistent index, required credentials, expected runtime, or failure behavior.

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

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

The description is front-loaded with a clear purpose sentence followed by a compact feature list. Most content earns its place, though the qualifier 'intelligent' and the specific average chunk count add minor promotional noise.

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 input schema is fully documented. However, the absence of annotations and usage guidance leaves operational context incomplete for a stateful indexing operation, particularly around prerequisites and side effects.

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 are already documented in the input schema. The description reinforces the incremental default and hints at force_rebuild behavior, but adds no syntax, limits, or interaction details beyond what the schema 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?

The description states a specific verb and resource: indexing a Zotero library. It also clarifies that the tool performs incremental updates and chunking, which distinguishes it from search-oriented siblings. However, it does not explicitly name or contrast itself with siblings such as search_fulltext or list_papers.

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

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

The description explains features but not when to use this tool versus alternatives. It does not say whether it should be run before searching, how often to run it, or what conditions favor a full rebuild over incremental indexing. The only implied guidance comes from the feature list, not explicit usage instructions.

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?

There are no annotations, so the description bears the full behavioral burden, yet it only notes that results are paginated (already implied by the limit/offset schema). Ordering, whether all indexed papers are returned, rate limits, and auth/permission requirements are all undisclosed.

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 verb, resource, return payload and pagination hint all appear immediately.

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

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

With an output schema present, return values need not be explained, and pagination is covered by the schema. However, for a tool sitting among five search/get siblings, the description leaves the agent without enough context to know when this enumerated listing is the right call versus a search.

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 limit, offset and their defaults/max are fully documented in the schema. The description adds no format or semantic detail beyond that, which is the expected baseline 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 and resource ('List indexed papers') plus what is returned (metadata) and the pagination nature. It is clear what the tool does, but it does not name or contrast any of the many search* siblings, so an agent must infer the boundary 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?

No statement of when to use this instead of 'search', 'search_fulltext', 'search_by_author', 'search_by_year', or 'get_collection_stats'. The description implies unfiltered enumeration only by omission, which is not explicit guidance.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it does almost none of it. A one-line statement omits cost/latency differences between sources, ranking behavior (RRF vs alpha weighting), and any limit or failure behavior; it relies entirely on the schema to convey mechanics, which is not the description's job.

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-formed sentence with the core operation front-loaded and no filler. It is efficient, though the extreme brevity leaves the tool under-explained relative to its nine parameters.

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 rich schema (100% coverage) and an output schema cover the mechanical details, so the description does not need to explain return values. What it still lacks is the contextual framing an agent needs: how this hybrid search relates to its four search_* siblings and which one to prefer.

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 every parameter — alpha, top_k, source, use_rrf, rrf_k_parameter, and the RRF weights — is documented in the schema with defaults and examples. The description adds no parameter meaning beyond that, so the baseline of 3 is appropriate.

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

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

States a specific verb and resource ('hybrid semantic + keyword search across research papers') that an agent can act on immediately. However, it gives no signal to distinguish it from siblings like search_fulltext, search_by_author, or search_by_year, which all search the same corpus by different means.

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 tool versus the sibling search tools. An agent must infer that 'hybrid' is the general-purpose option and that search_fulltext is the keyword-only path, which is never stated. No exclusions, prerequisites, or fallback conditions are given.

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 discloses only that results are paginated; it says nothing about matching behavior (left to the schema), ordering, whether all matching authors are collapsed, or any result caps, which matters for an unannotated search 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 efficient sentence that is front-loaded with the core action. It is appropriately sized for the tool, though 'all papers' mildly conflicts with the default limit of 50.

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 all three parameters. For a simple filtered-search tool this is nearly complete, with the only real gap being absence of routing guidance among the many sibling search 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 limit, offset, and author_name are all fully documented in the schema, including the case-insensitive partial-match semantics. The description adds no parameter meaning beyond that, making the baseline 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?

States a specific verb and resource ('Find all papers by a specific author'), which is clear on its own. It implicitly distinguishes itself from siblings like search_by_year and search_fulltext by naming the author dimension, but never names or contrasts those alternatives 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?

No guidance on when to prefer this over the sibling 'search', 'search_fulltext', or 'search_by_year'. The '(paginated)' parenthetical hints at a large result set but offers no context on when this tool is the right entry point.

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 adds only '(paginated)', which is already visible via limit/offset in the schema; it says nothing about ordering, whether a bare year is an exact match, permissions, or rate limits.

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

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

A single front-loaded sentence with zero filler; the scoping concept (year vs range) and pagination note are both stated in one pass.

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 all parameters are documented. The remaining gap is routing guidance among the many sibling search tools and any behavioral notes, which the description does not supply.

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 (year, start_year, limit, offset) are already documented, including that year doubles as the end year for a range. The description restates the range concept without adding syntax or format 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 (Find) and resource (papers) with the discriminating scope (publication year or year range), which is clearer than a generic search tool. It does not, however, distinguish itself from siblings like search, search_by_author, or search_fulltext, so an agent must infer the routing 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?

Usage is implied by the scope: use this when the filter is a publication year or range. There is no explicit when-not guidance and no mention of the sibling search tools that also return papers, leaving the agent to guess which search entry point to pick.

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 beyond capability: no auth/permission requirements, no rate limits, no cost difference between local and cloud sources, and no note on result ordering or pagination. Only the existence of matching modes is conveyed.

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 capability front-loaded and no filler. It is arguably too terse for a six-parameter tool, but as a conciseness judgment it wastes nothing.

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 six-parameter search tool with no annotations, the one-sentence description leaves major gaps: it does not help the agent disambiguate from the 'search' sibling or explain the local-vs-cloud source tradeoff. An output schema exists, so return values need not be described, but the selection and behavior gaps remain.

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 parameter meanings are already documented in the schema (top_k, source, combine_mode, pattern_type, etc.). The description hints at 'exact/regex/boolean logic', loosely mapping to pattern_type and combine_mode, but adds no syntax examples or format details 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 states a specific verb+resource ('full text search') and enumerates its matching modes (exact, regex, boolean). It is clear on its own, but it never distinguishes itself from the sibling tool 'search', so an agent cannot tell which search variant to pick from the description alone.

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 guidance, no exclusions, and no mention of the several sibling search tools (search, search_by_author, search_by_year). The agent is left to infer selection criteria entirely from the name.

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