Server Quality Checklist

Tool Scores

• list_filesA
  4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full behavioral disclosure. It thoroughly explains each file state, the meaning of 'stale_scheme' relative to staleChunkCount, and edge cases such as 'unreadable' requiring optional extras and data/url sources not having disk state. This is highly transparent and provides actionable context beyond simple read/write hints.

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

  Conciseness4/5

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

  The description is front-loaded with a clear one-sentence purpose, then elaborates on the various file states in a structured manner. It is somewhat long, but every sentence contributes to explaining the behavioral nuances. The paragraph format works well for the complexity, though it could potentially be split into a bulleted list for readability.

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

  Completeness4/5

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

  The description is remarkably complete regarding behavioral semantics, covering all state types and their implications for syncing. The output schema exists, so return format is not needed. However, the omission of the 'scope' parameter is a notable gap, leaving the only input parameter unexplained. This prevents full completeness for an agent selecting and invoking the tool.

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

  Parameters1/5

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

  The input schema defines a single optional 'scope' parameter with no description, and the tool description does not mention this parameter at all. With schema description coverage at 0%, the description must compensate, but it fails to do so. The agent is left without any guidance on what 'scope' means, how to format it, or what values are valid.

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

  Purpose5/5

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

  The description states the tool 'lists files found on disk under the document roots, plus indexed data/url sources', using a specific verb and resource. It distinguishes itself from sibling tools like read_file and delete_file by focusing on listing files with their indexing states rather than manipulating content.

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

  Usage Guidelines4/5

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

  The description provides clear context on when to use the tool: to inspect file states and determine which files need syncing. It explicitly notes that states other than 'ingested' and 'unreadable' require a sync_start, giving actionable guidance. However, it does not explicitly name alternative tools or specify when not to use this tool.

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

• query_documentsA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses topK clamping ('silently clamped to the cap rather than rejected'), the null parentId case and need to re-sync, and the displayPath/source distinction. It does not explicitly state read-only status, but 'search' implies it; still, it omits any mention of permissions or side effects.

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

  Conciseness4/5

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

  The description is long but well-organized, leading with a concise summary and then layering return-value details, usage advice, and citation formatting rules. Every sentence adds value, though the citation section is somewhat verbose. No redundant sentences.

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

  Completeness4/5

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

  Given the tool's complexity and rich output, the description covers return fields, topK limits, and edge cases like null parentId. The main gap is the undocumented `scope` parameter, which could lead to misinterpretation. Overall, it provides near-complete context for an agent.

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

  Parameters3/5

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

  The description adds explicit semantics for topK, including the clamping rule. It also clarifies the meaning of query output via the `text` field. However, it does not explain the `scope` parameter at all, despite zero schema descriptions, leaving its purpose and allowed values ambiguous.

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

  Purpose5/5

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

  Description clearly states 'Hybrid search: semantic similarity plus a keyword boost for exact terms.' It specifies the verb (search) and resource (documents), and distinguishes from sibling tools like read_file and list_files by focusing on ranked semantic search over chunks.

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

  Usage Guidelines4/5

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

  The description provides concrete usage guidance: 'Use `sources` to answer "which documents cover this topic" without inspecting individual chunks.' It also advises looking up `parentId` in `parents` when a match is too small to act on. However, it does not explicitly contrast with alternatives like read_file, leaving some room for ambiguity.

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

• ingest_dataA
  4.2/5.0
  Behavior4/5

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

  The description discloses an important behavioral trait: re-using the same 'source' replaces previously ingested content, making this an idempotent update operation. It also clarifies that 'source' is not a filesystem path, reducing potential misuse. With no annotations provided, this disclosure is valuable and goes beyond a simple 'ingest' label, though it does not mention other potential side effects or permissions.

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

  Conciseness5/5

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

  The description is exceptionally concise: two sentences, with each clause serving a purpose. It front-loads the core functionality and then adds essential details about format and source behavior without fluff or repetition.

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

  Completeness4/5

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

  Given the tool has an output schema, return values need not be explained. The description sufficiently covers the key usage context (in-memory content, source id semantics, replacement behavior, format options) for a simple 4-parameter tool. It could mention edge cases like empty data or size limits, but the current level is adequate for the tool's complexity.

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

  Parameters3/5

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

  The schema has 0% description coverage, so the description must compensate. It explains the 'format' parameter (explicitly listing allowed values and default) and 'source' (stable identifier, not a path, replacement semantics). However, 'data' and 'title' are not explicitly defined, though 'data' is inferable from the tool's purpose. This covers the most critical parameters but leaves some semantics implicit.

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

  Purpose5/5

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

  The description uses the specific verb 'Ingest' and clearly identifies the resource ('text/markdown/html content') and the namespace ('under a source id you choose'). It distinguishes itself from sibling tools like ingest_file and ingest_url by stating 'content the client holds', indicating raw in-memory content rather than files or URLs.

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

  Usage Guidelines4/5

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

  The description implies when to use this tool versus alternatives by specifying 'content the client holds', which differentiates it from file-based or URL-based ingestion. It also provides practical guidance on 'source' as a stable identifier and mentions the replacement behavior. However, it does not explicitly state 'use this when you have raw text as opposed to a file/URL', so it lacks an explicit exclusion.

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

• ingest_fileA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and explicitly discloses the destructive behavior: 'replaces any content already indexed' and 'discards its old chunks'. It also clarifies the re-ingesting semantics. It omits edge cases like error handling or permissions, but the key behavioral trait is well covered.

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

  Conciseness5/5

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

  The description is concise and front-loaded: the first sentence states the core purpose and effect, and the second provides the parameter constraint and re-ingesting detail. Every sentence earns its place with no redundancy.

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

  Completeness4/5

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

  The description is sufficiently complete for a simple single-parameter tool: it covers purpose, side effects, and the key constraint on filePath. Since an output schema exists, return values are not needed. However, it does not address sibling-tool differentiation or potential error/edge cases, leaving a minor gap.

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

  Parameters4/5

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

  The input schema has a single parameter with no description (0% schema coverage). The description compensates by adding the critical constraint that filePath must be an absolute path inside a configured document root, which gives the parameter clear semantic meaning beyond its type.

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

  Purpose5/5

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

  The description uses a specific verb ('Ingest or re-ingest') with a clear resource ('one file') and states the effect ('replacing any content already indexed'). It distinguishes from sibling tools like ingest_data and ingest_url by emphasizing 'file' and 'absolute path inside a configured document root'.

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

  Usage Guidelines3/5

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

  The description provides a clear precondition ('filePath must be an absolute path inside a configured document root') and implies usage for local files. However, it does not explicitly compare to alternatives like ingest_url or ingest_data, nor state when not to use this tool, leaving the differentiation implicit.

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

• read_chunk_neighborsA
  4.2/5.0
  Behavior3/5

  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 core behavior (reading neighboring chunks), the exclusive-choice constraint, and defaults for before/after. However, it does not mention edge cases such as invalid indices, what happens if both filePath and source are provided, or error conditions, leaving some behavioral ambiguity.

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

  Conciseness5/5

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

  The description is two sentences long, front-loads the purpose, and packs essential parameter guidance into the second sentence. Every word earns its place; there is no redundancy or filler.

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

  Completeness4/5

  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 are covered externally. The description covers the main usage scenario, parameter semantics, and constraints. It is missing a note about how to obtain chunkIndex from a search result and potential error handling, but overall it is sufficient for a tool of this complexity.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It explains filePath as an absolute path inside a document root, source as the id of a data/url item, and clarifies before/after counts and defaults. chunkIndex is only implied as the anchor but is understandable from context; still, it could have been explicitly defined.

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

  Purpose5/5

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

  The description uses the specific verb 'Read' and clearly identifies the resource as 'chunks immediately before and after a search result.' This distinguishes it from sibling tools like read_file (which reads a single file) and query_documents (which searches), making the tool's purpose unambiguous.

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

  Usage Guidelines4/5

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

  The description provides explicit parameter usage guidance: 'Provide exactly one of filePath... or source' and explains how before/after control the number of chunks. It implies use after a search result but does not explicitly state when not to use it or name alternative tools, so it stops 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.

• ingest_urlA
  4.4/5.0
  Behavior4/5

  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 reveals key behaviors: the tool makes network requests, restricts schemes to http/https, blocks private/local hosts, and has an environment variable to override that restriction. It also explains the source parameter's default behavior. It does not cover error handling or authentication, but the output schema may address return values.

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

  Conciseness5/5

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

  The description is concise at four sentences, with the primary action front-loaded. Every sentence adds value: the core function, scheme/address constraints, the network-exclusivity differentiator, and source parameter semantics. There is no fluff or repetition of schema fields.

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

  Completeness4/5

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

  The tool is moderately complex (network fetch, security restrictions, indexing), and the description covers the critical contextual aspects: what it does, URL restrictions, the private-address bypass, and how source affects indexing. The existence of an output schema reduces the need to document return values. It does not mention title semantics, rate limits, or authentication, but these may be less critical or covered elsewhere.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It adds meaning for 'source' (defaults to the URL, controls the index key, enables updates) and makes 'url' self-evident from the core action. However, the 'title' parameter is not explained, leaving a gap for a required schema without any descriptive support.

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

  Purpose5/5

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

  The description clearly states the tool's function with a specific verb and resource: 'Fetch an http(s) URL, convert it to Markdown, and index it.' This distinguishes it from siblings by explicitly noting it is the only tool that reaches the network, while every other tool works on local files and the local index.

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

  Usage Guidelines5/5

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

  The description provides explicit usage context: it is the sole network-reaching tool, implying it should be used when remote content needs to be ingested. It also notes an exclusion (private/local addresses are forbidden) and a workaround (set ALLOW_PRIVATE_URLS=1), giving clear guidance on when this tool is appropriate versus alternatives like ingest_file or ingest_data.

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

• statusA
  4.4/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it always includes version, conditionally includes roots/dbPath/model/hybridWeight/counts or indexError/configError, explains chunkScheme, staleChunkCount, schemeWarning, ocr engine status, and ocrHint. This goes well beyond a simple status report and covers expected edge cases.

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

  Conciseness5/5

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

  The description is front-loaded with a one-sentence summary, then organized into logical paragraphs for valid/invalid configuration, chunk scheme, and OCR. Each sentence adds unique value—no filler or repetition—making it appropriately sized for the information conveyed.

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

  Completeness5/5

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

  The description covers all major behaviors and edge cases: invalid configuration, index open failure, chunk scheme staleness, and missing OCR extras. Since an output schema exists, it doesn't need to detail return values, but it still explains the meaning of key fields, making it complete for a status tool in a complex setup.

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

  Parameters4/5

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

  The tool has zero parameters, and the input schema is an empty object. The description adds no parameter-specific semantics because none are needed. Baseline for 0 params is 4, which fits here.

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

  Purpose4/5

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

  The description clearly states the tool reports configuration and index status, with a specific verb and resource. It also distinguishes itself implicitly by noting it works even when configuration is invalid, which sets it apart from other tools, though it does not explicitly name alternatives like sync_status.

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

  Usage Guidelines4/5

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

  The description provides clear context for when to use this tool: it works even when configuration is invalid, and it notes that every other tool raises an error referencing configError until fixed, implying this is the diagnostic tool. However, it does not explicitly say 'use this instead of X' or list alternative tools by name.

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

• delete_fileA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden for behavioral disclosure. It explicitly states that deletion 'only removes the index entry' and that files left in a document root are 're-ingested by a later sync_start.' This is a significant non-obvious behavior that warns the caller about the temporary effect for files under document roots.

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

  Conciseness5/5

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

  The description is two short sentences: the first states the purpose, the second gives parameter constraints and a behavioral caveat. Every clause adds value, with no redundant phrasing or filler.

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

  Completeness5/5

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

  The tool has only two parameters, a clear purpose, and an output schema. The description covers the action, parameter selection, and a crucial side-effect (re-ingestion), which is sufficient for correct tool selection and invocation. No further context is necessary.

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

  Parameters5/5

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

  Schema coverage is 0% (no descriptions in the input schema), so the description must compensate. It defines 'filePath' as 'absolute path inside a document root' and 'source' as 'the id of a data/url item,' and enforces exclusivity ('Provide exactly one of'). This fully clarifies the two nullable parameters and their intended use.

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

  Purpose5/5

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

  The description begins with 'Delete an indexed file, data item, or url item from the index,' which uses a specific verb and resource. It clearly distinguishes the tool from siblings like ingest_* (add), query_documents (search), and read_file (view), leaving no ambiguity about its role.

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

  Usage Guidelines4/5

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

  The description provides clear parameter-usage guidance: 'Provide exactly one of filePath ... or source,' which is essential for correct invocation. It does not explicitly contrast when to delete versus sync_start or others, but the purpose is self-evident and the instruction implies the tool is for index removal, not file-system operations.

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

• sync_statusA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden. It discloses that only the latest job is retained, that stale or pre-restart jobIds raise errors, and that unreadable counts are not failures—detailed behavior beyond the input schema and likely important for correct usage.

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

  Conciseness5/5

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

  The description is compact yet comprehensive, with three paragraphs each serving a purpose: purpose, return values, and edge cases. No redundant statements; the first sentence front-loads the main function.

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

  Completeness5/5

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

  Given the simple one-parameter input and the existence of an output schema, the description covers the essential behavioral nuances: retention policy, error conditions, and the special meaning of unreadable counts. It is sufficient for an agent to invoke the tool correctly and interpret results.

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

  Parameters4/5

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

  The schema only documents a required string 'jobId' with no description (0% schema coverage). The description compensates by explaining that jobId refers to a job from sync_start and that old IDs will error, giving lifecycle context. It doesn't explicitly say where the ID comes from, but it is implied.

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

  Purpose5/5

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

  The description opens with 'Poll a sync job started by sync_start,' using a specific verb ('Poll') and resource ('sync job'). This clearly distinguishes it from siblings like sync_start (which starts) and status (general), and it also enumerates the returned state and counts, reinforcing the exact function.

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

  Usage Guidelines4/5

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

  It states the tool is for polling a job 'started by sync_start,' indicating the intended workflow context. However, it does not explicitly mention when not to use it or compare it with the sibling 'status' tool, so the guidance is clear but lacks explicit alternatives or exclusions.

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

• sync_startA
  4.9/5.0
  Behavior5/5

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

  Without annotations, the description carries full burden, and it excels: it discloses async behavior (returns jobId immediately), side effects (ingests new/changed files, skips identical, removes vanished), retention policy (only latest job kept, restart discards), and concurrency rules (only one sync, others fail). No contradictory annotations.

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

  Conciseness5/5

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

  Although longer than typical, each paragraph addresses a distinct aspect: purpose, async/behavior, and concurrency. No redundant statements—all information is operationally relevant, making the length justified.

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

  Completeness5/5

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

  For a tool with one optional parameter and an output schema, the description covers purpose, return type, failure modes, concurrency, and side effects. It is complete enough for an agent to invoke correctly and know what to expect.

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

  Parameters4/5

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

  The schema's only parameter 'path' has zero description coverage; the description compensates by explaining that it refers to 'document roots (or one path inside them)', clarifying the default null means syncing all roots and a string restricts to a subpath. It adds meaningful semantics beyond the raw schema, though it doesn't provide format specifics like absolute vs relative paths.

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

  Purpose5/5

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

  The description opens with a specific verb 'Reconcile' and clearly identifies the resource (index/document roots). It distinguishes itself from sibling tools like sync_status and ingest_file by explaining what sync_start does (full or partial reindex) versus polling status. The purpose is unmistakable.

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

  Usage Guidelines5/5

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

  It explicitly instructs to poll sync_status for the job result, and warns that a sync already in progress will cause immediate failure with an identifying message. It also notes that single-file ingests and queries are never blocked, implying they can be used concurrently. This gives clear when-to-use and when-not-to-use context.

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

• read_fileA
  5/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden. It discloses non-obvious behavior — document reconstruction from chunks rather than concatenation, deduplication of repeated context, full response size, and large-response caveat. This is substantial 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.

  Conciseness5/5

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

  The description is front-loaded with a clear purpose, then explains the non-obvious reconstruction behavior in a compact paragraph, and ends with usage guidance. Every sentence earns its place; no filler or repetition of schema fields.

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

  Completeness5/5

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

  Given the tool's moderate complexity and lack of annotations, the description is complete: it covers purpose, exact parameter semantics, behavioral quirks, response size, and provides a sibling alternative. The presence of an output schema reduces the need to describe return values, yet it still notes the response holds full document text.

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

  Parameters5/5

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

  Schema coverage is 0%, but the description adds full meaning: filePath is 'absolute path inside a document root' and source is 'the id of a data/url item.' It also enforces mutual exclusivity, which the schema itself doesn't express.

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

  Purpose5/5

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

  The description opens with 'Read a source's entire indexed content as Markdown' — a specific verb and resource. It clearly distinguishes from sibling read_chunk_neighbors by noting that tool is preferred for chunk-level context.

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

  Usage Guidelines5/5

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

  Explicit guidance is provided: 'provide exactly one of filePath or source' and 'prefer read_chunk_neighbors when only the context around one chunk is needed.' This tells the agent when to use this tool vs an alternative.

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