Server Quality Checklist

Tool Scores

• exportA
  3.5/5.0
  Behavior2/5

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

  No annotations are present, so the description must carry the behavioral disclosure burden. It does disclose that this is a SELECT-based export and that it writes to a local file, but it does not mention whether existing files are overwritten, whether directories are created, or any other side effects or limitations.

  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, well-structured sentence with no fluff. It front-loads the core action and includes both the destination and supported formats without wasting words.

  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?

  The description is minimally sufficient for an agent to invoke the tool: it identifies the query type, the output formats, and the fact that results go to a local file. However, with no annotations and no output schema, it lacks behavioral context like file overwrite semantics or how this compares to returning query results directly.

  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 four parameters clearly. The description adds little beyond reinforcing that the output is JSON or CSV and the file is local, which is already captured by the schema. Baseline 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 names a specific action—execute a SELECT query—and a distinct resource outcome: exporting results to a local file as JSON or CSV. This clearly separates it from sibling tools like query or execute, which return results rather than writing files.

  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 the tool should be used when file export is needed, but it does not explicitly compare against alternatives such as query, query_paginated, or multi_query, nor does it state when not to use it. The usage context is inferable but not explicit.

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

• room_infoA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It tells what metadata is shown, and 'Show' implies a read-only operation, but it does not explicitly state side effects, error conditions, or that no modification occurs. This is adequate but not deeply transparent.

  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, front-loaded sentence conveys the tool's purpose and outputs with no wasted words. Every part contributes meaning.

  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 one-parameter metadata tool, the description is mostly complete: it specifies the required input and lists the expected output contents. The absence of an output schema means the return structure isn't described, which is a minor gap, but overall the tool is simple enough that this is not crippling.

  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 'database' as a filename with an example. The description adds no additional parameter semantics, 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 clearly states a specific verb ('Show') and resource ('Room database metadata') and enumerates the returned contents (schema version, identity hash, managed entities). It distinguishes itself from sibling tools like list_tables/describe_table by focusing on Room-specific metadata rather than general table structure.

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

  Usage Guidelines2/5

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

  The description provides no explicit guidance about when to use this tool versus alternatives such as list_tables/list_databases. It implies usage for retrieving Room metadata but never states contexts, exclusions, or selection criteria relative to siblings.

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

• query_paginatedA
  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 disclosure burden. It does add useful behavior: the LIMIT/OFFSET pagination style and the total-row-count return value. It does not state read-only semantics, how the total is computed, or behavior on invalid SQL, which are meaningful gaps given zero annotation coverage.

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

  Conciseness5/5

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

  Two short sentences, front-loaded with the action and scoping. No wasted words — defines what it does (SELECT with pagination) and what it returns (results + total count).

  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?

  With no annotations and no output schema, the description covers the essential purpose and return shape but leaves gaps: how to pass dynamic values, whether the total reflects pre- or post-pagination, and what happens for non-SELECT statements. Adequate for selection, thinner for invocation edge cases.

  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 baseline is 3. The description confirms the limit/offset pair maps to LIMIT/OFFSET pagination, which adds a little nuance, but it does not explain parameterization, quantifiers, or value syntax 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?

  Clear verb+resource: executes a SELECT query with LIMIT/OFFSET pagination, and explicitly discloses it returns results plus total row count. The pagination scoping distinguishes it from a pplain query tool.

  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?

  Usage is implied by the pagination focus — an agent can infer this tool should be chosen when LIMIT/OFFSET pagination is needed. However, there is no explicit when-to-use/when-not-to-use guidance or named alternatives among siblings like query or describe_table.

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

• list_tablesA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral disclosure burden. It adds useful context with 'Pulls a fresh copy from the device,' indicating the operation retrieves current data rather than relying on a cached copy. However, it does not mention whether the operation is strictly read-only, what the return value looks like, or any connectivity/device requirements.

  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 convey purpose and behavioral context with no filler. The core function is front-loaded, and the second sentence adds a meaningful detail without bloating the description.

  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 one-parameter list operation, the description is adequate: it names the action, the target resource, and the freshness behavior. The schema covers the required input. It could be slightly more complete by specifying the output format, but 'List all tables' makes the likely return type (a list of table names) sufficiently clear.

  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 input schema already fully documents the single 'database' parameter with a clear example ('app.db'), so baseline applies. The description adds no additional parameter-specific meaning, but none is needed given the high schema coverage.

  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 states a specific action and resource: 'List all tables in a SQLite database.' This clearly differentiates it from siblings like list_databases and describe_table, which target databases and table schemas respectively. The tool's purpose is immediately obvious.

  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?

  Usage is implied by the purpose: use this when you need the list of tables in a given SQLite database. However, the description does not explicitly contrast it with sibling tools such as describe_table or query, nor does it state when not to use it. No exclusionary guidance is provided.

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

• multi_queryA
  3.9/5.0
  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 disclosure burden. It does disclose a key trait: the tool is read-only and executes multiple SELECT queries in one call. However, it does not explain behavior around partial failures, result ordering, execution semantics, or any limits. This is minimal but non-tautological behavioral information.

  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 with no fluff. The core action and read-only constraint are front-loaded, and the second sentence adds a direct efficiency comparison with the sibling tool. Every word earns its place.

  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?

  The tool has only 2 simple parameters, both fully documented in the schema, and no output schema exists. The description clearly conveys the operation but omits any mention of the return shape, how results correspond to the input queries, error behavior, or limitations. For a multi-query tool, some return-format guidance would strengthen completeness.

  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%: both `queries` and `database` are already described clearly in the input schema. The description adds no parameter-level meaning beyond what the schema provides. The baseline of 3 applies because the schema already fully explains the parameters, and the description doesn't conflict or add confusion.

  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 action: 'Execute multiple read-only SQL SELECT queries in a single call.' It clearly identifies the resource (SQL SELECT queries) and differentiates itself from the sibling tool `query` by emphasizing 'multiple' and 'single call.' No ambiguity remains about what the tool does.

  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 by positioning the tool as 'More efficient than calling query multiple times.' This tells the agent when to use multi_query instead of making repeated `query` calls. It does not explicitly mention alternatives like `query_paginated` or `execute`, but the read-only SELECT scope and efficiency rationale give adequate usage direction.

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

• describe_tableA
  4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the disclosure burden. The verb 'Show' clearly conveys a read-only operation, and enumerating columns/types/constraints sets expectations for the result. Missing details like behavior on an unknown table are minor for this simple introspection 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 front-loaded sentence with no filler; every phrase ('Show the schema', 'columns, types, constraints', 'for a specific table') contributes to selection and invocation. It is short without being vague.

  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 two-parameter tool with no output schema and no annotations, the description adequately conveys what the result will contain and which table is targeted. It lacks an explicit statement about return format and failure behavior, but the simple scope makes that gap minor.

  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%, so the input schema already documents both table and database parameters. The description adds no parameter-specific detail beyond 'specific table,' so baseline 3 is appropriate because the schema does the heavy lifting.

  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 ('Show') and resource ('schema for a specific table'), and enumerates what it returns ('columns, types, constraints'). This clearly distinguishes it from siblings like list_tables, which only enumerate table names, and schema_diff, which compares schemas.

  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 'for a specific table' implies when to invoke it (single-table schema inspection) and implies it is not for listing all tables. However, it does not explicitly contrast with alternatives such as list_tables or schema_diff, so the when-to-use guidance is largely left to inference.

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

• queryA
  4/5.0
  Behavior4/5

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

  With no annotations present, the description carries the full behavioral burden. It discloses that the operation is read-only, returns results as JSON, and pulls a fresh copy from the device before querying. This gives useful, non-obvious behavioral context beyond a simple 'run query' statement.

  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 three short sentences, each conveying essential information: the operation type, the output format, and the data freshness behavior. 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?

  For a simple two-parameter read-only query tool, the description covers the core behavior, output format, and a notable implementation detail. It could mention alternatives or limitations, but nothing critical is missing for an agent to invoke the tool 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?

  The schema covers 100% of parameter descriptions, so the baseline is 3. The description does not add additional meaning to the sql or database parameters beyond what the schema already provides, which is acceptable given the high schema coverage.

  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 executes a read-only SQL SELECT query, which is a specific verb and resource. The phrase 'read-only' helps distinguish it from sibling tools like execute that may allow write operations, even though the sibling is not named explicitly.

  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 usage for read-only SQL SELECT queries, providing some context. However, it gives no explicit guidance on when to choose this tool over siblings like query_paginated, multi_query, or execute, nor does it mention any exclusions.

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

• schema_diffA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It states that the tool 'Shows added/removed tables and columns,' which conveys the core behavior, but it does not explicitly state that it is read-only, whether it has side effects, or how results are structured beyond that high-level summary.

  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 concise sentences with no filler. The primary purpose is front-loaded, and the second sentence adds useful output scope without unnecessary verbosity.

  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?

  This is a simple two-parameter comparison tool with no output schema, and the description covers the essential return insight: added/removed tables and columns. It does not describe exact output formatting or error behavior, but for a tool of this complexity the description is reasonably 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?

  The input schema already fully describes both parameters with 'Old database filename' and 'New database filename,' giving 100% schema coverage. The description adds no additional parameter-level detail, 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 and resource: 'Compare schemas of two databases.' It further specifies what the tool shows (added/removed tables and columns), making its purpose unmistakable and clearly distinct from sibling tools like list_tables or describe_table.

  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 communicates the scenario for using this tool: comparing two database schemas. It does not explicitly name alternatives or exclusions, but the context is clear enough that an agent would know when this tool is appropriate.

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

• executeA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It does more than say 'execute SQL' by revealing the pull-modify-push mechanism: 'Pulls the database, modifies it locally, then pushes it back to the device,' which warns agents this is not a direct remote write. It does not cover failure or rollback behavior, but the central behavioral trait is visible.

  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 dense sentence with no filler. The first clause states the action and scope, and the second gives the important execution mechanism, so every clause earns its place. It is front-loaded with the operation type.

  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 two-parameter write tool the description is mostly adequate: it names the write scope, the parameters are schema-documented, and the pull-modify-push mechanism is explained. However, there is no output schema and no mention of what the caller should expect back, such as affected rows or success/error results, nor how push failures are reported. These are notable gaps for a mutation tool with no annotations.

  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 input schema has 100% parameter coverage, with descriptions for both 'sql' and 'database'. The description adds no new parameter details beyond narrowing 'sql' to INSERT/UPDATE/DELETE, which is already in the schema. This meets the baseline for schema-covered parameters.

  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 action and target: 'Execute an INSERT, UPDATE, or DELETE SQL statement.' This clearly identifies the write-only scope and differentiates it from sibling query tools by naming the SQL statement types. The title and parameter schema reinforce the same purpose.

  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 states exactly when to use the tool: for data-modifying SQL operations (INSERT/UPDATE/DELETE). It does not explicitly name query or multi_query as the alternative for SELECT statements, but the stated operation types make the boundary clear. This is clear context without an explicit when-not or exclusion.

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

• list_devicesA
  4.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It correctly states the scope ('connected via ADB') and the action is inherently read-only, but it does not mention output format, failure modes, or whether it includes offline/unauthorized devices. This is adequate but not richly transparent.

  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, direct sentence conveys the entire functional scope without wasted words. The key resource and method are front-loaded, making the definition easy to scan and interpret.

  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 zero-parameter list operation with no output schema, the description is sufficiently complete. There are no complex inputs, side effects, or sibling ambiguities requiring additional explanation.

  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 zero properties and 100% schema coverage, so the schema fully documents the absence of parameters. The description adds no parameter-specific meaning, but none is needed; the baseline of 4 for zero-parameter tools 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 ('List') and resource ('Android devices/emulators connected via ADB'), making the tool's function unambiguous. It clearly distinguishes from the sibling database-oriented tools, which all operate on packages, databases, tables, and queries.

  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 tool is for listing ADB-connected devices, providing enough context for when to use it. It does not explicitly exclude alternatives, but no sibling tool is a plausible substitute for device enumeration, so the usage context is effectively clear.

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

• list_packagesA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. The verb 'List' clearly implies a read-only operation, and the scope is specified as installed third-party packages on the device. It does not mention output format or side effects, but there is no indication of destructive 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?

  Two short sentences with no filler. The main action and resource are front-loaded, followed by a practical purpose. Every sentence 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 zero-parameter read-only listing tool, the description is sufficient: it states what is listed, where, and why it is useful. Without an output schema, a slightly more explicit return-value statement would help, but the package-name purpose strongly implies the output.

  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 there are no parameter semantics to document. The baseline of 4 applies because no compensation is needed; the schema already fully covers the empty parameter set.

  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 ('List') with a clear resource ('third-party packages installed on the device'), which directly distinguishes it from siblings like list_databases, list_tables, and list_devices. An agent can immediately tell what this tool does.

  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 provides a clear use case: 'Useful for finding the correct package name.' It does not explicitly say when not to use it or name alternatives, but for a simple package-listing tool the context is clear enough.

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

• list_databasesA
  4.5/5.0
  Behavior4/5

  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 discloses a read-only listing operation over a well-defined scope and emphasizes 'all' files, which helps an agent understand the un-filtered nature. It does not mention output shape or empty-result behavior, but those are minor for a zero-parameter list 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 of about twelve words that front-loads the verb and resource. Every element — all, SQLite, database files, Android app, package ID — adds useful information without redundancy.

  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 parameterless listing tool with no output schema, this description is complete. An agent knows what the tool operates on, the scope, and the intended result. Nothing critical is missing for correct 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 description has nothing to add beyond the schema. Baseline 4 applies because there are no parameter semantics to explain.

  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 ('List') and resource ('all SQLite database files') with an explicit scope: the Android app com.hortusys. This clearly distinguishes it from siblings like list_tables and describe_table, which operate at a different level.

  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 makes the usage context clear: call this tool to enumerate the SQLite database files belonging to the specified app. It does not explicitly name alternatives or exclusions, but the resource type and app scope are specific enough to guide selection.

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