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

Beyond the readOnlyHint annotation, the description discloses key behaviors: cursor-based pagination, sort order (newest first), and the semantic definition of a play as one resume chain. It also explains that a show media_id matches all its episodes, which is important behavioral context not available in the 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?

The entire description is just two sentences, yet it packs in the tool's purpose, output granularity, ordering, all filter semantics, and pagination usage. There is no filler or repetition; every phrase adds value.

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 the tool's complexity (13 parameters, no schema descriptions), the description covers every parameter, explains pagination, and provides output semantics. The presence of an output schema means return values need not be described. This is complete and self-sufficient.

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 schema has no descriptions for its 13 parameters, but the description lists and explains each filter, including domain-specific meanings like canonical id vs rating_key, and enumerates valid media_type values. It also clarifies date formats for since/until and the cursor parameter. This fully compensates for the lack of schema descriptions.

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

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

The description clearly states that this tool returns watch history with specific characteristics: cursor-paginated, newest first, one record per play with canonical media identity. It also defines a play as one resume chain, which uniquely identifies this tool and distinguishes it from sibling tools like get_user_history or get_media_history that focus on scoped history.

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 provides clear context: this is a general history listing with a wide range of filters, including user_id, server_id, media_id, and external IDs. It explains how to paginate by passing meta.nextCursor back as cursor. However, it does not explicitly mention when to prefer this tool over alternatives like get_user_history or get_media_history.

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?

The readOnlyHint annotation already indicates a safe read operation. The description adds behavioral detail explaining that the tool normalizes various ref formats into a canonical identity and computes availability, which goes beyond the annotation and helps set expectations.

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 two sentences, front-loads the core purpose, and then gives necessary format details. Every word earns its place; no fluff or repetition.

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 available, the description focuses on input semantics and the general resolution result. It is sufficient for an agent to invoke correctly, though it doesn't explain edge cases or error behavior, which is acceptable given the output schema.

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

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

The schema has zero description coverage for the 'ref' parameter, but the description fully compensates by explaining the exact accepted formats (canonical uuid or type-qualified provider ref), including concrete examples. This provides complete semantic meaning for the parameter.

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 clearly states the action ('Resolve a media ref') and the output ('canonical identity, merged ids, and per-server availability'). This is specific and distinguishes it from sibling tools like get_media_history or get_media_children, which focus on different aspects.

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 concrete context on when to use the tool by specifying the acceptable ref formats and what resolution entails. It doesn't explicitly name alternative tools or when not to use it, but the context is clear enough for an agent to decide.

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?

The `readOnlyHint` annotation already declares this a safe read operation, and the description adds behavioral nuance by distinguishing between canonical media UUIDs and provider refs, plus the constraint that seasons are UUID-only. This goes beyond the annotation without contradicting it.

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 sentences, front-loaded with the primary action and resource. Every clause adds information: list behavior, episode counts, ref type, and the UUID-only constraint. No wasted words.

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

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

The description covers the tool's dual behavior and ref constraints, and an output schema exists to document return values. It is slightly ambiguous whether a movie ref would error or return nothing, but for a simple list tool this is adequately 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?

The schema provides only a bare `ref` string with no description, so the description carries the full load. It explains that `ref` can be a canonical media UUID or a provider ref and specifies that seasons are UUID-only, giving the agent actionable parameter guidance.

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 opens with a specific verb ('List') and names the exact resources ('a show's seasons' or 'a season's episodes'), which clearly distinguishes this from sibling tools like history or stats. It also notes episode counts, adding useful scoping detail.

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 implies the appropriate use case by explaining that the tool lists child media items (seasons or episodes) and clarifies the `ref` format. It does not explicitly exclude alternatives or mention when not to use it, but the context is clear enough for an agent.

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?

The description adds behavioral context beyond the readOnlyHint annotation by explaining the cursor-paginated mechanism and instructing to pass meta.nextCursor back as the cursor. This discloses pagination behavior and iterative usage, which is useful and not present in annotations.

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 concise and well-structured: two sentences that front-load the core purpose and then provide essential parameter details. No wasted words.

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 the presence of an output schema and simple parameter set, the description is largely complete. It explains pagination and accepted ref formats, which are the key operational details. It does not repeat what the output schema likely covers, and no major gaps are evident.

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?

With 0% schema coverage, the description compensates by explaining the 'ref' parameter (canonical media uuid or provider ref) and the 'cursor' parameter (pass meta.nextCursor back). However, 'page_size' is not explicitly described, though its default value and pagination context imply 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?

The description clearly states the tool's action: retrieving cursor-paginated watch history for a single media item. This distinguishes it from sibling tools like get_user_history (user-specific) and get_history (likely all history) by specifying 'single media item'.

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 provides clear context for when to use the tool: for watch history of a single media item. It does not explicitly name alternatives or exclusions, but the context is clear enough to guide selection among the sibling tools.

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

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

Annotations declare readOnlyHint=true, so the read-only nature is covered. The description adds valuable behavioral context by detailing the time windows (all_time, last_30, last_7) and the combined/per-server breakdown structure, which goes beyond the annotation and explains what kind of data to expect.

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, well-structured sentence that front-loads the key metrics, then windows, breakdown, and parameter semantics. Every part adds value with no redundancy or filler.

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 the simple one-parameter schema, readOnly annotation, and existence of an output schema, the description fully covers the tool's purpose and data shape. There are no missing critical details like auth or side effects, and the parameter semantics are addressed.

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 input schema has 0% description coverage, so the description must compensate. It does so by defining 'ref' as 'a canonical media uuid or a provider ref', which is critical semantic information not present in the schema. This helps the agent understand what value to pass, though it could further clarify the format or provenance of provider refs.

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 clearly states the tool returns play counts, watch time, and distinct viewers for a media item, with time windows and combined/per-server breakdowns. This specifies the resource (media item) and the exact metrics, distinguishing it from sibling tools like tracearr_get_media_history or tracearr_get_user_stats.

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

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

The description implies the tool is used when you need viewing statistics for a media item, and the 'for a media item' phrase gives context. However, it does not explicitly state when to use this over alternatives or mention any exclusions, so usage guidance is only implied rather than explicit.

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?

The readOnlyHint annotation covers the safety profile, and the description adds useful behavioral details like ordering and window defaults. However, it does not disclose potential limitations (e.g., pagination, authorization, or data freshness) beyond the annotation.

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 compact and front-loaded, using two sentences to convey the core purpose and parameter details without any wasted words.

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 that an output schema exists and the tool is read-only, the description covers the essential aspects: what it returns, parameter semantics for the main input, and ordering. The missing server_id context is a minor gap given the simplicity of the tool.

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

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

With 0% schema coverage, the description explains 'window' values and defaults, and clarifies 'ref' as a media UUID or provider ref. However, 'server_id' is left unexplained, leaving a gap for one of the three parameters.

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 clearly states what the tool returns: per-account watchers of a media item, ordered by watch time. This specific resource and ordering distinguishes it from sibling tools like history or stream tools.

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 is given on when to use this tool versus alternatives. It does not mention use cases, exclusions, or references to sibling tools, so the agent must infer the appropriate context.

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?

The description adds behavioral detail beyond the readOnlyHint annotation by explaining the effect of summary=true (returns only summary stats, omits data array) and that streams carry canonical media identity. This gives useful context about output shape and parameter behavior without contradicting the annotation.

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

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

Three short sentences, front-loaded with the core purpose, and no redundant or filler content. Every sentence adds information: purpose, output characteristics, and parameter behavior.

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 the output schema exists to describe return values, the description adequately covers the main use case and summary option. The only apparent gap is the server_id parameter's role, which could affect completeness for users wanting to filter by server.

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 description explains the summary parameter's effect (returns summary stats, omits data array), but does not mention server_id at all, leaving its meaning or filtering behavior unclear. Since the schema descriptions are absent, the description should compensate more fully for both parameters.

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 clearly states the tool returns 'Currently active playback sessions across all servers,' which is a specific verb+resource+scope. It distinguishes from sibling tools like tracearr_get_history or tracearr_get_media by focusing on live streams rather than historical or static media data.

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 context is clear: this is for active playback sessions across all servers. However, it does not explicitly mention when not to use it or name alternative tools, so it misses the explicit exclusion criteria that would earn a 5.

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

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

The readOnlyHint annotation already declares the operation safe, and the description adds the conceptual output ('correlation block') without contradicting the annotation. However, it does not disclose edge-case behaviors such as behavior for invalid or unknown IDs, which would be useful beyond the annotation.

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 concise sentence with no filler, front-loading the verb 'Resolve' and the key object. Every word adds value, making it an example of efficient writing.

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, the description does not need to explain return values. The tool is simple (read-only, one parameter), and the description sufficiently covers the tool's purpose and input semantics. It could mention not-found behavior, but that is not essential given the straightforward nature of the tool.

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

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

The schema provides only a string 'id' with no description, but the description explicitly calls it a 'Tracearr identity id', adding domain meaning and telling the agent the expected semantic. It does not specify format or source, but given a single parameter, this is adequate compensation for the 0% schema coverage.

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 ('Resolve') and clearly identifies the resource ('Tracearr identity id to its correlation block'), with a parenthetical explaining what a correlation block is. This distinguishes the tool from siblings like tracearr_get_user_history and tracearr_get_user_stats by focusing on correlation-block resolution.

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 implies the use case: when you have a Tracearr identity id and need its correlation block, use this tool. It does not explicitly name alternatives or exclusions, but the purpose statement is sufficiently clear for an agent to infer the appropriate context relative to sibling tools.

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?

Beyond the readOnlyHint annotation, the description adds valuable behavioral context: cursor-based pagination and the need to pass meta.nextCursor back as the cursor. It also clarifies that history spans all accounts owned by the identity, which is non-obvious.

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 that is concise, front-loaded with the main purpose, and contains no filler. It efficiently communicates the scope and pagination behavior.

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 the presence of an output schema and read-only annotation, the description covers the essential aspects: what the tool does, its scope, and pagination handling. It does not describe the output shape (covered by schema) or the required id type (evident from schema), so it is sufficiently complete for 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?

With 0% schema description coverage, the description partially compensates by explaining the cursor parameter ('Pass meta.nextCursor back as cursor') and implying that 'id' is the identity identifier. However, it does not elaborate on page_size or the exact format of id, leaving some gap.

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 clearly states the tool retrieves 'Cursor-paginated watch history for an identity, scoped to every account it owns.' This is a specific verb+resource+scope, and the term 'user_history' alongside 'identity' distinguishes it from the sibling tracearr_get_history.

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 implies usage for fetching watch history for a specific identity, but it does not explicitly mention when to prefer this over tracearr_get_history or tracearr_get_media_history, nor does it state any 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?

The description adds meaningful behavioral context beyond the readOnlyHint annotation: it states the aggregation across all owned accounts, the three time windows, and the inclusion of top genres. This transparently reveals the tool's computational scope and output composition without contradicting the annotation.

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, information-dense sentence that covers the primary metrics, aggregation behavior, time windows, and an additional output dimension. Every clause contributes useful information, and the text is front-loaded with the core action.

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 the simple parameter list and the presence of an output schema, the description is largely sufficient for correct invocation. It outlines all key behavioral dimensions, though it does not address edge cases like how empty results or non-existent identities are handled, nor does it explicitly advise against using this tool for detailed history.

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 sole id parameter is described only as 'for an identity', which gives minimal semantic meaning beyond the bare string type in the schema. It does not clarify the source or format of the identifier, nor does it connect it to other tools like list_users, but it does establish that the ID represents the identity whose stats are being fetched.

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 clearly identifies the tool as one that returns plays and watch time for an identity, aggregated across accounts and time windows, plus top genres. This specific verb+resource combination distinguishes it from siblings like get_media_stats or get_user_history, which focus on media-level or historical detail.

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 provides no explicit guidance on when to use this tool instead of alternatives. There is no conditional language, no mention of alternatives, and no indication of scenarios where this tool is preferred or not preferred, leaving the agent to infer usage.

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?

readOnlyHint is already true, so the description doesn't need to state read-only. It adds the specific content of the rollups, but doesn't disclose details like response format or pagination. This is similar to get_calls in the calibration, which received a 3 for transparency.

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 one concise sentence that front-loads the purpose ("Per-library rollups") and enumerates the key counts without waste. Every word contributes meaning, making it an excellent example of efficient specification.

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 and readOnlyHint annotation present, the description sufficiently covers the tool's functionality for an agent to select it correctly. It has no parameters, and the description clearly communicates the library-level scope, making it complete in context.

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

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

There are zero parameters, so the description needn't explain any. The baseline for 0 parameters is 4, and the description doesn't need to compensate for any omitted schema info. It simply describes the output scope.

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 "Per-library rollups" with explicit counts (item/movie/episode/show/track, total file size, per-resolution counts), making it clear this is a list/aggregate operation for libraries. It distinguishes from sibling tools like tracearr_get_media_stats by focusing on library-level rollups rather than per-media stats.

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

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

The description implies usage when library-level aggregate statistics are needed, but it doesn't explicitly mention when to use vs alternatives like tracearr_get_media_stats or tracearr_get_media. It gives no exclusion criteria, leaving the agent to infer the appropriate context.

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

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

Annotations already indicate read-only. Description adds valuable behavioral details: cursor pagination, ordering, server-reported added date, and include_removed behavior for tombstones. These go beyond the annotation and help set expectations.

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 concise sentences: the first states the core function and ordering, the second enumerates filters and the include_removed option. No redundant information or filler.

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 list tool with output schema present, the description covers the main usage, filters, and a special behavior. It doesn't elaborate on cursor mechanics or return shape, but these are sufficiently covered by schema and standard pagination understanding.

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 has 0% param descriptions, but the description explains the purpose of key filters (server_id, library_id, media_type) and the include_removed flag. Cursor and page_size are left to standard pagination knowledge, which is acceptable.

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?

Description clearly states the tool lists library items ordered by server-reported added date, newest first, with specific filters. It distinguishes itself from sibling tools by its focus on recently added items and pagination style.

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?

Provides clear context for use: listing recently added items with filtering by server, library, and media type. Does not explicitly mention alternatives or when not to use, but the purpose is distinct enough among 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?

The readOnlyHint annotation already signals a safe read operation. The description supplements this with concrete behavioral details: newest-first ordering, cursor pagination, account correlation being Tracearr-side, and the exact semantics of include_removed. This adds meaningful transparency beyond the annotation, though it does not discuss cursor expiration or other potential edge behaviors.

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, dense sentence that front-loads the primary behavior, then appends pagination/filter semantics. Every clause adds value, and there is no repetition of schema fields or annotations.

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

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

An output schema is present, so return-value details are covered. The description covers key behavioral aspects: ordering, pagination, account ownership, and the removed filter. It lacks explicit usage guidance or alternatives, but given the schema and annotation, the description is sufficiently complete for a list tool.

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

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

With 0% schema description coverage, the description carries the burden of parameter explanation. It explicitly clarifies include_removed and the phrase 'Cursor-paginated' explains cursor's role, but page_size is not mentioned. The parameter names and defaults are self-evident, yet the description only partially compensates for the missing schema descriptions.

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

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

The description opens with 'Cursor-paginated Tracearr identities, newest first' which clearly identifies the resource (Tracearr identities) and the core list/pagination behavior. It distinguishes itself from sibling tools like tracearr_get_user (singular retrieval) and tracearr_get_history by specifying identity-level listing with owned media-server accounts.

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 implies a list/browse use case by describing pagination and the optional include_removed filter, but it does not explicitly state when to use this versus alternatives, nor does it provide exclusions or contrast with tools like tracearr_get_user. Usage context is present but not fully articulated.

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