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

No annotations provided, so description carries full burden. It discloses the return type (TaosSqlResponse) and scope (current Taos configuration). However, it fails to mention read-only safety, error conditions (e.g., connection failures), or side effects, which are critical for a database tool without annotation hints.

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?

Brief and mostly front-loaded with the Returns section providing structured output documentation. Slightly odd indentation in the Returns block, but generally efficient with no redundant sentences. Could be more compact.

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?

Appropriate for a zero-parameter listing tool where output schema exists (per context signals). The description mentions TaosSqlResponse, complementing the structured output schema. Missing guidance on the sibling tool ecosystem prevents a higher score.

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?

Zero parameters present. Per scoring rules, 0 params = baseline 4. The description mentions 'current Taos configuration' implying context-dependency, but does not explicitly document why no parameters are needed or what context is used.

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

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

States specific action (Get) and resource (databases), expanding 'dbs' from the name. Mentions 'current Taos configuration' which provides useful scope context. However, it does not explicitly differentiate from siblings like get_all_stables (which gets super tables) or query_taos_db_data (which queries 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?

Provides no guidance on when to use this versus alternatives like switch_db (which changes context) or query_taos_db_data (which queries contents). No prerequisites or error conditions mentioned despite the implicit dependency on current Taos configuration 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?

No annotations provided, so description carries full burden. It discloses nothing about read-only status, permission requirements, performance characteristics, or what the TaosSqlResponse contains. The description is purely functional without behavioral context.

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

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

Uses standard docstring format (Args/Returns) which is structured and readable. No extraneous text. However, the Returns section is redundant given that an output schema exists and the description appears in the main description field rather than being separated.

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?

Adequate for a single-parameter tool with full schema coverage and output schema present. However, given the lack of annotations and the potential cost/scope of 'get all' operations in database contexts, it could disclose more about safety or result set size.

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

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

Schema coverage is 100%, establishing baseline 3. The Args section duplicates the schema description almost exactly ('Default is None which means the configured database' vs 'Defaults to None... configured database is used'), adding no additional semantic value like valid naming conventions or examples.

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

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

States 'Get all stables' which clearly identifies the verb and resource, but is essentially a restatement of the function name. It fails to distinguish from sibling tools like query_taos_db_data (which queries data) or get_all_dbs (which gets databases), and does not clarify what a 'stable' (super table) is in this context.

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 no guidance on when to use this tool versus alternatives like query_taos_db_data or get_field_infos. Does not mention whether to use switch_db first or if db_name parameter obviates that need.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the return type (TaosSqlResponse) but fails to disclose whether the operation is read-only, what happens if the stable does not exist (error behavior), or whether rate limits apply. The Returns section merely restates the output without behavioral context.

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

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

The docstring format with Args/Returns sections is structured but unnecessarily verbose given the schema already provides this information. The first sentence earns its place, but the Args section repeats schema content verbatim rather than adding value, and the Returns section provides minimal information beyond the type name.

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 has an existing output schema (per context signals) and 100% input schema coverage, the description meets minimum viability by identifying the tool's purpose. However, it lacks operational completeness (error handling, side effects) expected for a tool with no annotations to supply that 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?

Schema description coverage is 100%, establishing a baseline of 3. The description largely duplicates the schema (e.g., 'The name of the stable' and the db_name default behavior) without adding significant semantic context such as valid naming patterns, case sensitivity, or examples that would help the agent formulate correct inputs.

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 'Get the field information of the specified stable,' providing a specific verb and resource. It clearly distinguishes from siblings like get_all_stables (which lists stables) and query_taos_db_data (which queries row data), though it could explicitly clarify this retrieves schema metadata rather than 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?

No guidance is provided on when to use this tool versus alternatives, prerequisites (e.g., whether the stable must exist), or workflow hints (e.g., 'use get_all_stables first to discover valid stable_name values'). The description only explains what parameters are accepted, not usage strategy.

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

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

With no annotations provided, the description carries the full disclosure burden. It successfully declares the 'read-only' safety trait, but omits other behavioral details like result set limits, error handling for invalid SQL, or connection pooling behavior that would help an agent anticipate failure modes.

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 uses Python docstring formatting (Args/Returns) which is redundant given the structured input schema and existence of output schema. While the 'Important' prefix effectively front-loads the read-only constraint, the Args/Returns sections waste tokens by repeating fully-documented schema information.

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 single-parameter query tool with complete schema coverage and an existing output schema, the description is sufficiently complete. It identifies the target database system and operation type adequately, though mentioning SQL dialect specifics or result size limits would improve it.

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 Args section describes sql_stmt as 'The sql statement you want to retrieve data from taos db', which is verbatim repetition of the schema description. With 100% schema coverage, this meets the baseline score of 3 without adding additional syntactic or semantic guidance (e.g., expected SQL dialect features).

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 executes a 'read-only SQL query' on the specific 'Taos database' resource. The 'read-only' qualifier is specific and distinguishes it from potential write operations, though it could better differentiate from sibling metadata tools like get_field_infos.

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 'read-only' constraint provides basic usage guidance (do not use for INSERT/UPDATE), but there is no explicit guidance on when to choose this over sibling metadata tools like get_all_stables or how to construct valid queries for this specific SQL dialect.

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?

Discloses the underlying SQL command (`USE`) and return type (TaosSqlResponse), which is helpful. However, with no annotations provided, it fails to disclose critical behavioral traits: whether the switch affects only the current session, persists across subsequent tool calls, or validates the database existence before switching.

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?

Uses structured Python docstring format with clear Args/Returns sections. The Returns section is somewhat redundant given the existence of an output schema, but the overall structure is logical and the purpose statement is appropriately front-loaded.

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?

While the output schema handles return value documentation, the description lacks crucial context for a state-modifying tool: relationship to sibling query tools (prerequisites?), session scope, and error conditions. Adequate but incomplete for proper orchestration.

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

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

Schema coverage is 100%, establishing a baseline of 3. The description repeats the parameter description almost verbatim from the schema ('The name of the database to switch to') without adding format constraints, validation rules, or examples beyond what the schema already provides.

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

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

States the specific action (switch) and target resource (database) clearly. However, it could better distinguish from 'get_all_dbs' by clarifying this changes the active session context rather than just retrieving information.

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 explicit guidance on when to call this versus alternatives, or whether it's required before 'query_taos_db_data'. The agent cannot determine if database switching is mandatory for queries or if queries can specify database names inline.

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

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

With no annotations, the description adequately explains return behavior (empty dict if not exists, boolean-valued dict if exists) and implies context-sensitivity ('current' configuration). However, it omits error handling details (e.g., behavior if no database is selected).

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?

Uses Python docstring format (Args/Returns) which is readable but not optimized for MCP conventions. The '**Important**' prefix is unnecessary dramatic flair, and the return value explanation is verbose relative to the simple operation.

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 single-parameter existence check with an output schema present, the description provides sufficient detail about the return data structure and boolean semantics, adequately preparing an agent to interpret results.

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?

Input schema has 100% coverage with 'stable_name' fully documented. The Args section in the description essentially repeats the schema information without adding additional semantic context or usage examples, meeting the baseline expectation.

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?

Clearly states it checks existence of a 'stable' in the current Taos database with specific action verb and resource identification. However, note the terminology mismatch: the tool name uses 'table' while the description consistently uses 'stable' (super table), which could cause confusion.

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?

Fails to provide when-to-use guidance relative to sibling 'get_all_stables' (which lists all stables vs. checking one). While it mentions 'current' database configuration, it doesn't explicitly state prerequisites like requiring 'switch_db' to be called first.

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