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

Goes beyond the annotations by disclosing that there is no row cap (so unbounded reads can blow up memory), that transactions are supported, and that database functions can have side effects — consistent with destructiveHint=true and openWorldHint=true rather than contradicting them. It does not explain what read-only enforcement actually blocks or how results are buffered, which keeps it short of a 5.

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 short, front-loaded sentences, each carrying distinct information: scope, capabilities, the row-cap/alternative routing, and the side-effect warning. The phrase 'Read-only statement checks and transactions are enabled' is compressed to the point of mild ambiguity.

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

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

With an output schema, full schema coverage, and rich annotations, the description only needs to add operational guidance, which it does via the row cap, LIMIT advice, and side-effect caveat. 'Small results' is left unquantified, so the agent has no concrete threshold for switching to stream_query.

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%, so both sql and params are already documented including the ? placeholder convention. The description restates the 'one statement' constraint and the LIMIT advice, adding no syntax or value-mapping detail beyond the 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?

States a specific verb and resource ('Run one SQL statement') and immediately scopes the intended result size plus the SHOW/DESCRIBE/EXPLAIN case. It also distinguishes itself from the sibling stream_query by pointing to LIMIT-then-stream as the alternative for large results.

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?

Gives both the when ('small results', metadata statements) and the explicit alternative ('add LIMIT or use stream_query'), which is the exact routing decision an agent faces among these siblings. Nothing about selection is left to inference.

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

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered. The description adds genuinely new behavioral facts: it fails on absent or invisible tables and it does not inspect views, which prevents wasted calls. It does not discuss visibility/permission implications further, keeping it just short of a 5.

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

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

Two sentences, front-loaded with the positive scope followed by the negative boundaries, and no filler. Every clause carries information the agent needs.

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

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

An output schema exists so return values need no explanation, and annotations cover the safety profile. The remaining burden, scope boundaries and failure conditions, is fully addressed.

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

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

Schema description coverage is 100%, so both tableName and schemaName are already fully documented in the schema, including quote handling and default schema behavior. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 a specific verb (inspect) and resource (one existing table) plus the exact returned fields: columns, nullability, constraints, owner. The scope is narrow and distinct from the listing siblings like list_tables and list_views.

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?

"before composing SQL" gives a clear triggering context, and the exclusions ("does not read table data", "does not inspect views", fails if absent) tell the agent when not to use it. It never names the sibling tools explicitly, so routing to list_views or execute_query still requires inference.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral detail beyond them: no pagination, all projection-column catalog rows returned, and a semantic caveat that isUnique reflects key-constraint status rather than a uniqueness proof. This is material context for interpreting results.

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

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

Three short sentences, front-loaded with purpose, then return behavior and the isUnique caveat. 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.

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

With an output schema, annotations, and full parameter coverage, the description is nearly complete. The only gap is explicit routing against get_table_structure, which would help an agent pick the right inspection 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 coverage is 100%, with tableName and schemaName fully documented, so the baseline is 3. The description adds scope ('one table') but no syntax or format detail beyond the 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?

States a specific verb and resource: inspect one table's Vertica projections and column sort positions. The name 'list_indexes' is clarified by the description's projection framing. It is clear, though it does not explicitly differentiate itself from get_table_structure or list_views.

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?

Usage is implied by 'one table's Vertica projections', but there is no explicit when-to-use guidance, prerequisites, or named alternative such as get_table_structure. The agent must infer the appropriate context from the sibling list.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description's added value is in the operational details: results are unpaginated and table data is not read. 'Visible tables' also signals that access control can limit the result set, which no annotation conveys.

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 tight sentences, each carrying distinct information: purpose and workflow position first, then the result-scope and no-data-read caveats. No filler and nothing repeated from the schema or annotations.

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

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

For a one-parameter read tool with rich annotations and an output schema, this covers everything an agent needs: scope (one schema), result set size (unpaginated), visibility filtering, and the fact that no table data is returned. Nothing material is left to guesswork.

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 single schemaName parameter is fully documented in the schema (100% coverage), including the default-schema fallback when omitted. The description adds nothing about parameters, so the baseline of 3 applies.

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 gives a specific verb and resource ('Discover visible tables in one schema'), which separates it from list_views and list_indexes by the object type being listed. It does not, however, explicitly contrast itself with those siblings or with get_table_structure.

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?

'before querying' implies a workflow position, so an agent can infer this is a discovery step that precedes stream_query or execute_query. There is no explicit when-not-to-use guidance and no sibling named as an alternative, leaving selection to inference.

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

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

Annotations already declare read-only, idempotent, closed-world behavior, so safety is covered. The description adds genuinely non-obvious behavior: no pagination, all visible matches returned, and the definition/fullDefinition preview-vs-complete distinction that prevents an agent from truncating SQL.

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 short sentences, purpose first, then the return-behavior caveat. Every clause carries information an agent would otherwise have to discover by trial.

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

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

An output schema exists, so return shape needn't be restated; the description still flags pagination absence and the preview-field caveat, which are the main pitfalls. Only the sibling-routing guidance is missing.

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% and the schema description already explains the default-schema fallback and the no-quotes rule. The description only echoes the single-schema scoping, adding nothing new about the parameter.

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

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

"Discover views and their SQL in one schema" gives a specific verb and resource, and the SQL-definition mention separates it from list_tables/list_indexes. It never names those siblings, so differentiation is inferred rather than stated.

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?

Usage is only implied: an agent can infer this is the lookup for views scoped to a single schema. No explicit when-to-use, prerequisites, or alternatives (e.g., get_table_structure, list_tables) are mentioned.

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?

Adds real context beyond the annotations: single execution, batches returned together, no continuation cursor, and an explicit warning that functions can have side effects, which is consistent with destructiveHint=true and readOnlyHint=false. The ORDER BY advice and the no-cursor caveat are exactly the kind of behavior an agent cannot recover from structured fields.

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 short sentences, each carrying distinct information: scope, execution model, ordering guidance, side-effect warning. No repetition and the selection condition 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?

With a full output schema and annotations covering the safety profile, the only thing the description must supply is the batch-versus-stream execution model, and it does that clearly along with the side-effect caveat. Minor gap: it never positions itself explicitly against execute_query, which is the sibling an agent will most likely confuse it with.

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%, including defaults, bounds, and the maxRows truncation caveat, so the schema already carries the parameter burden. The description adds only the ORDER BY reproducibility hint, which is behavioral rather than a parameter detail. Baseline 3 applies.

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 a specific capability: bounded SELECT/WITH executed once, returning batches in a single response with no cursor. That distinguishes it in substance from execute_query, but the sibling is never named, so the agent must infer the pairing from the tool name alone.

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?

"Use for bounded SELECT/WITH results valid inside a subquery" gives a positive selection condition, and "no cursor or incremental streaming" implicitly rules out paginated workloads. It stops short of an explicit when-not or a named alternative such as execute_query.

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