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

No annotations provided; description covers batch creation, failure skipping, and ERD updates, but does not disclose destructive nature, permissions, or rollback behavior.

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?

Efficient, front-loaded sentences with no unnecessary words; every sentence 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?

Covers batch creation, failure, and context, but misses return value description and deeper error handling, which is important given no 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?

Schema coverage is 100%, so description adds minimal per-parameter meaning; the batch and failure reporting context is helpful but not substantial beyond schema.

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 'Create one or more new tables' with specific verb and resource, distinguishing it from sibling tools like modifyTables or listTables.

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 explains batch creation, failure handling, and context usage, but lacks explicit guidance on when to use versus alternatives like modifyTables or executeQuery.

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 covers key behaviors: supported statements, DDL exclusion, row limit for SELECT/EXPLAIN, and context usage. Could be more explicit about side effects of write operations, but overall transparent.

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?

Four well-structured sentences, each adding value. Purpose stated first. No redundant or unnecessary 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?

Covers return behavior (up to 200 rows for SELECT/EXPLAIN), parameter context, and sibling tools. Lacks explicit statement that INSERT/UPDATE/DELETE return no rows, but implied. Good overall.

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% with clear descriptions for each parameter. Description adds context about 'current context' for connectionId and schema, which is not in schema alone.

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 verb 'execute', resource 'SQL query on database', and specific supported statement types (SELECT, INSERT, UPDATE, DELETE, EXPLAIN). It explicitly distinguishes from sibling tools by disallowing DDL and referencing createTables/modifyTables.

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 explicit guidance on when to use (for DML and SELECT/EXPLAIN) and when not (DDL). Names alternatives (createTables, modifyTables) and explains context 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?

No annotations provided, so description must disclose all behavioral traits. Does not state whether tool is read-only, has side effects (e.g., writing files), error behavior (e.g., missing table), or required permissions. Only states it returns file contents.

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 focused sentences: purpose, context requirement, output. No redundant words, information is 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?

Covers purpose, context, and return type, but lacks details on error conditions, valid template packs, prerequisite setup for context, and return format specifics. Adequate for a simple 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?

Schema has 100% parameter description coverage, so baseline is 3. Description adds context about schema omission using current context, but does not elaborate on tableName or templatePackId beyond schema.

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 verb 'generate source code' and resource 'from a database table using a template pack'. It distinguishes from siblings like createTables (table creation vs code generation) though not explicitly.

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?

Implied usage: use when generating code from a table. Mentions current context for connection, but no explicit when-not-to-use or alternatives 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?

No annotations are provided, so the description carries the full disclosure burden. It accurately describes the tool as providing information, which is clearly non-destructive. While it lacks explicit safety notes, the simplicity of the tool (no params, no mutations) makes this sufficient.

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 with no wasted words. It front-loads the core purpose ('Get information...') and efficiently adds contextual guidance about related tools and configuration, making every sentence earn its place.

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 simplicity (no parameters, no output schema), the description is complete. It explains its purpose, suggests when to use siblings, and provides practical advice for managing IDs. No additional information is needed.

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 no parameters, so the baseline is 4. The description adds value beyond the empty schema by explaining what the tool returns and how it fits into the larger workflow, though it doesn't need to document non-existent 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 'Get information about how to find project and connection IDs,' which is a specific verb and resource. It distinguishes itself from siblings like listConnections (which discovers MCP-enabled pairs) by focusing on informational guidance rather than executing queries or modifications.

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 explicit when-to-use context (finding project/connection IDs) and references an alternative tool (listConnections) for discovering MCP-enabled pairs. It also advises on setting defaults and passing IDs per tool call, covering both usage scenarios and best practices.

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. Description fails to disclose behavioral traits such as side effects, authentication requirements, or idempotency. 'Get' implies read-only, but no confirmation or details.

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?

Extremely short but wasteful; it merely restates the name. Conciseness should provide value, not redundancy. Could include a brief explanation in the same length.

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 tool with no parameters and no output schema, the description must fully explain its purpose and return value. 'Get Mcp-Session-Id' is insufficient—it does not define what the session ID represents or how it is used.

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?

No parameters in schema (100% coverage by default). Description adds no parameter-level insight, but given zero parameters, there is no information gap. Baseline 4 is not warranted because description does not proactively clarify anything.

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 'Get Mcp-Session-Id' is a tautology of the tool name. It does not specify the resource or action beyond what the name already implies, providing no additional clarity.

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 on when to use this tool versus siblings (e.g., listConnections, ping). The description lacks context for appropriate invocation scenarios.

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 exist, so the description must disclose behavior. It mentions that schema/connection falls back to current context, which is helpful. It does not mention error handling, permissions, or performance implications, but for a read-only query tool, the level is acceptable.

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, no redundancy. information is front-loaded and each sentence adds new, useful information. Perfectly concise.

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 only 3 parameters, one required, and no output schema, the description sufficiently explains the tool's purpose and usage scope. It covers the return types (columns, indexes, etc.) and context inheritance, leaving little ambiguity.

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 100% coverage, so baseline is 3. The description adds meaningful context beyond the schema: the ability to pass multiple table names and the fallback behavior for connectionId/schema.

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 it retrieves detailed information about tables (columns, indexes, primary keys, foreign keys) and supports multiple tables in one call. This distinguishes it from sibling tools like listTables (which likely lists only names).

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 tells when to use the tool (to get detailed table info), implies context usage, and indirectly suggests that listTables is for simpler listings. However, it does not explicitly exclude cases like schema inspection vs. data retrieval.

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 fully discloses that only MCP-enabled connections are returned and details each entry's fields. It is transparent about the per-user profile and per-schema policies, but could mention if any restrictions or pagination exist.

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 with two sentences. It front-loads the main action and then elaborates on the content, making it easy to read.

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 no parameters or output schema, the description provides all necessary context: purpose, filter, returned fields. It is fully complete for an agent to decide and invoke 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 tool has no parameters (100% schema coverage), so no parameter documentation is needed. The description adds no parameter info, which is appropriate.

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 lists database connections with MCP access enabled in the current NeoSQL project. It specifies the filter (only opted-in connections) and lists what each entry includes, distinguishing it from siblings like listTables.

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 explicitly advises to use this tool to discover connectionId and schema values for other tools, providing clear guidance on when to use it. However, it does not mention alternative tools or when not to use it.

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 are provided, so the description must cover behavioral aspects. It implies a read-only operation but does not explicitly state non-destructiveness or any side effects. It mentions using current context, which adds transparency, but could be more explicit about safety or permissions.

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

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

Two sentences that front-load the purpose and return value, with no redundant information. Every sentence earns its place.

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 simple listing tool with fully documented parameters and no output schema, the description covers the essential information (what is returned, fallback behavior). It could mention error handling or pagination, but is largely 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 input schema already provides 100% description coverage for all three parameters. The description only repeats the fallback behavior already in the schema, adding no significant new meaning.

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 purpose: listing tables and views in a database schema, specifying the returned data (table names, types, comments). This distinguishes it from siblings like getTableDetails (detailed info on one table) or createTables.

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 explains that parameters are optional and fall back to current context, providing clear usage guidance. However, it does not explicitly contrast with alternatives like getTableDetails or state when not to use this tool.

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

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

With no annotations, the description must disclose behavior. It explains operational details (e.g., dropping every PK column requires explicit DROP). However, it does not mention whether the operation is transactional, whether changes are immediately persisted, or any permission requirements. Some behavioral traits are left implicit.

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 verbose and lists all operation types, making it thorough but not concise. It is front-loaded with the main action, but subsequent sentences are dense. It could be trimmed without losing meaning.

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 (many operation types) and that the input schema covers all parameters, the description covers the main use cases and edge cases (e.g., empty comments, PK drops). Missing details like error handling or atomicity are minor gaps, but overall it is mostly 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?

Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by explaining the purpose of each operation group and providing usage nuance (e.g., when to set modify flag, how to handle PK drops). This elevates the score above baseline.

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 modifies existing tables and enumerates all supported operation types (rename, comments, PK, columns, indexes, foreign keys, constraints). It distinguishes from sibling tools like createTables (creates new tables) and getTableDetails (reads table info).

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 specific usage patterns, such as using remarksOperation.modify=true to intentionally set an empty comment, and that omitting primaryKeyOperations or passing [] means no change. It also mentions that multiple alterations can be batched and notes context defaults, but lacks explicit when-not-to-use guidance vs. alternatives.

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, but description fully discloses behavior: returns 'pong'. No side effects or additional traits needed.

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 with zero waste, properly 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?

For a simple health-check tool with no output schema, the description is complete enough to understand function and return value.

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?

No parameters in schema, baseline is 4. Description adds nothing about parameters, but none exist.

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 it is a health-check tool that returns 'pong', which is specific and distinct from siblings that handle database operations.

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 when to use or when not, but the purpose is obvious; implicit usage as a health check. Lacks alternatives or exclusions.

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