Server Quality Checklist

Tool Scores

• get_monologue_of_the_dayA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral burden. It usefully clarifies that 'of the day' means the most recently posted item on social feeds, which is a meaningful behavioral nuance. However, it does not explicitly state that the operation is read-only, has no inputs, or describe any freshness/caching behavior.

  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 a single concise sentence with no filler. The key clarifying fact, 'most recently posted to the site's social feeds,' is front-loaded and immediately resolves ambiguity in the tool name.

  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?

  For a zero-parameter getter with no output schema, the description is almost complete: it names the resource and defines the selection criterion. It could be even stronger by explicitly saying it returns the monologue text, but the current phrasing is sufficient for basic invocation.

  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, so the baseline is 4. The description does not need to explain parameters, and it adds the relevant selection rule (most recent) that governs what the tool returns.

  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 identifies the exact resource ('Monologue of the Day') and defines it as the most recently posted piece, which distinguishes it from random_monologue and search_monologues. However, it lacks an explicit verb like 'retrieves' or 'returns,' so it reads as a definition rather than an operation statement.

  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 implies this tool should be used when the agent needs the current or most recently posted monologue. It does not explicitly mention when not to use it or refer to sibling tools such as random_monologue or get_monologue, leaving routing partially implicit.

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

• get_play_summaryA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It does disclose one important behavior: the result 'May be null if not generated yet.' But it does not explain why generation might not have happened, whether calling the tool triggers generation, or any caching/permission characteristics.

  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 a single front-loaded sentence that states the action, the resource, and the key null behavior with no filler. Every clause earns its place.

  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?

  For a simple single-parameter getter, the description covers the essential resource and the nullable return. However, because there is no output schema, a bit more context about what the summary contains or when generation occurs would make it more complete.

  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 100%, and the schema already documents 'play' as 'Play title (exact or partial).' The description adds only examples, not additional semantic meaning, so the baseline score of 3 is appropriate.

  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 ('Fetch') and a specific resource ('an AI-generated summary of a play'), with concrete examples like 'Hamlet' and 'The Tempest'. It clearly distinguishes itself from siblings such as get_scene_summary by scoping to play-level summaries.

  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 intended use is implied by the purpose itself: use this when you need a summary of a play. However, the description gives no explicit guidance about when to prefer it over alternatives like get_scene_summary or how it relates to get_monologue/list_plays.

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

• list_all_monologues_for_a_characterA
  3.9/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the burden. It does disclose the matching precedence ('exactly first, then as a substring') and the exhaustive list scope, but it does not mention return format, result ordering/pagination, or limit behavior beyond what the schema already states.

  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?

  Two focused sentences, front-loaded with the main action and scope, with every sentence contributing concrete information. No filler or redundant restating of the schema.

  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?

  For a simple two-parameter list tool with full schema coverage, the description provides the essential invocation information: target character, matching semantics, and examples. It lacks return-shape/pagination details, but those are not strictly required to select and invoke the tool.

  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 coverage is 100%, so the baseline is 3. The description adds value by giving example values and explaining how the character parameter is matched (exact, then substring), which is not in the schema. The limit parameter gains no descriptive additions.

  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?

  Clear verb-resource pair: 'List every monologue spoken by a given character', with concrete examples. It is easily distinguishable from siblings like get_monologue or random_monologue, but the description does not explicitly differentiate itself from search_monologues, so it falls short of a 5.

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

  Usage Guidelines4/5

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

  The context for using the tool is obvious from the purpose and examples: when you need all monologues for a specific character. It does not explicitly state when not to use it or point to an alternative sibling, though the exact-then-substring matching note provides useful selection/use context.

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

• get_paraphrased_monologueA
  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 behavioral burden and does it well by revealing that the paraphrase is AI-generated, may be null, and that the url preserves the monologue. It doesn't cover errors or latency, but for a simple read operation the key fallback behavior is disclosed.

  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?

  Two sentences, with the main purpose first and the null caveat second. No filler; every clause adds information about output, generation status, or fallback behavior.

  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?

  For a tool with two straightforward parameters and no output schema, the description covers the return concept, the null case, and the URL fallback. It could specify exact response property names, but an agent can infer enough to invoke it correctly.

  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 coverage is 100%, with id and monologue_id already described. The description adds no parameter behavior beyond naming the resource, so it meets the baseline but does not elevate it.

  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 clear verb and resource: 'Fetch a monologue's full text alongside its modern-English, line-by-line paraphrase.' This is unambiguous and the paraphrase element distinguishes it from the sibling get_monologue, even though that sibling is not named.

  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?

  It implies the tool is for retrieving text plus paraphrase, and it warns the paraphrase can be null, which is useful. However, it never states when to prefer this over get_monologue or other siblings, nor gives any explicit 'use instead' routing.

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

• get_scene_summaryA
  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 usefully reveals that the summary is AI-generated and may be null if not generated yet, which is important for setting expectations. It does not mention read-only status or response shape, but 'Fetch' strongly implies a read operation.

  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 one front-loaded sentence that states the core operation immediately, followed by a valuable caveat about null returns. Every word earns its place.

  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 definition is complete enough for a simple fetch tool: it states what the tool returns and the null condition. It relies on the schema to explain parameter aliases, which is acceptable, though it could explicitly note that a monologue id is expected despite required parameters being zero.

  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 100%, with both parameters fully described in the schema itself. The tool description adds no new parameter-level semantic information, 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.

  Purpose5/5

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

  The description uses a specific verb ('Fetch') and resource ('AI-generated summary of the scene a monologue appears in'), and clarifies it is context for the speech. This clearly differentiates it from siblings like get_play_summary and get_paraphrased_monologue.

  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 phrase 'context for the speech' implies when to use it, but there is no explicit guidance about when to prefer this over related tools like get_play_summary or get_paraphrased_monologue. No exclusions or alternatives are named.

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

• search_monologuesA
  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 burden. It discloses that this is a read-oriented search and specifies the return shape ('matches, each with a permalink url'). It does not detail matching case-sensitivity or filter combination, but for a simple search tool this is adequate.

  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?

  Two short sentences with no wasted words. The main purpose is front-loaded and the return format is stated compactly.

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

  Completeness3/5

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

  For a read-only search tool with all-optional, fully documented parameters, the description is adequate. However, with eight siblings and no output schema, it does not clarify when to prefer this over list_all_monologues_for_a_character or enumerate the result fields beyond url.

  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 100%, so the schema already documents all six parameters. The description reinforces the query matching behavior but adds no meaning beyond what the schema provides.

  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 a specific verb ('Search'), a clear resource ('Shakespeare monologues'), and the exact matching scope (character, play, first line). This distinguishes it from sibling tools like get_monologue or list_all_monologues_for_a_character.

  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 clearly frames when to use it: free-text search with optional filters. It establishes the tool's general role but does not explicitly name alternatives or exclusion conditions.

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

• get_monologueA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden itself. It usefully discloses that the tool returns only a catalogue entry, not the full text, and instructs the agent to follow the returned url. This adds meaningful behavioral context beyond 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.

  Conciseness5/5

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

  Two short sentences with no filler. The main action and key follow-up step are front-loaded, and every word earns its place.

  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?

  For a simple read-by-id tool, the description is mostly complete: it states what to pass, what to expect (a catalogue entry), and what to do next. The absence of an output schema means return-field details are not spelled out, but the critical follow-the-url behavior is covered.

  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 100%, so the schema already documents both id and monologue_id. The description's 'numeric id' adds little beyond the schema's integer type, so the baseline of 3 applies.

  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 ('Fetch') and resource ('one monologue's catalogue entry') and identifies the key selector ('by its numeric id'). This clearly distinguishes it from siblings like search_monologues and random_monologue.

  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 clearly indicates this is the tool to use when you already have a specific numeric monologue id, especially reinforced by the schema's reference to search_monologues. It does not explicitly name alternatives or exclusions, but the usage context is clear.

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

• list_playsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden, and it does disclose the read-only nature ('List') and the exact returned data (classification and monologue counts). It does not mention ordering or the exact response shape, but those are minor for a no-argument listing tool.

  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?

  A single sentence that front-loads the action and resource and packs the output details without any filler or repetition. Every word adds information useful for selecting or invoking the tool.

  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?

  For a parameterless list tool, the description states the essential return information sufficiently even without an output schema. It could add a bit more precision about the response format or ordering, but nothing required to make the call is missing.

  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?

  There are no parameters, so the empty schema is fully covered and there is no parameter semantics to elaborate. The description's field list concerns the response rather than arguments, which is appropriate for a no-arg call.

  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 names a specific operation ('List'), a precise resource ('Shakespeare's plays'), and the output fields (classification and monologue counts). This clearly sets it apart from the monologue-scoped siblings and from get_play_summary, which implies a different granularity.

  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 purpose implies when to use it—whenever a caller needs an overview of all plays rather than a specific monologue or scene—but it does not explicitly state alternatives or exclusions. No sibling is named, so the agent must infer the choice from the tool name and verb.

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

• random_monologueA
  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 burden, and it discloses the key behavior: the tool returns one random result and supports optional filters. 'Return' implies a read-only operation, so there is no hidden mutation or destructive side effect.

  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?

  Two short sentences front-load the core action and filters, followed by the practical use case. Every sentence earns its place with no 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?

  The tool is simple, has no required parameters, and the schema covers all input semantics. Since there is no output schema, 'one random monologue' provides a sufficient return contract for invocation, though it does not describe no-match behavior.

  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 100%, so the schema already documents both parameters thoroughly, including exact-or-partial play titles and gender value handling. The description only restates that the filters are optional, adding little semantic value beyond the schema.

  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 'Return' with a clear resource, 'one random monologue,' and names the optional filters. The word 'random' immediately distinguishes it from sibling tools like get_monologue or search_monologues.

  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 gives an explicit when-to-use context: 'Useful for a suggestion when the user is undecided.' It does not explicitly name alternatives or when not to use it, but the random-selection framing makes the appropriate use clear.

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