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

Annotations already mark it read-only and idempotent, and the description adds substantial behavioral detail beyond that: live INFORMATION_SCHEMA with bundled snapshot fallback, a 'source' field indicating which was used, found=false plus closest-name suggestions for unknown views, and domain traps about wh_task and time-related views. This gives the agent valuable runtime expectations.

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 longer than average but every sentence earns its place: it front-loads the core action, then supplies usage, fallback behavior, error handling, and critical domain traps. There is no filler or repetition of annotation/schema content.

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-value explanation is unnecessary; the description nonetheless covers source selection, failure behavior, domain-specific data traps, and a pointer to the ID-resolution guide. For a tool operating on a warehouse schema, this gives an agent everything needed to call it correctly.

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 documents the single view parameter with examples, and schema coverage is 100%. The description reinforces that the name must be exact and come from list_views, but adds no new parameter-level semantics beyond the schema, so it stays at the 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 opening sentence states a specific action and resource: 'Return the column names and SQL types of ONE warehouse view.' This clearly separates describe_view from siblings list_views (enumerate views) and query (run queries), so an agent immediately knows 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.

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

The description explicitly tells the agent when to call it — 'before writing a query' — and instructs it to use the exact view name from list_views, retrying with suggested names if the view is unknown. It does not explicitly spell out when not to use the tool versus query, but the purpose and prerequisite provide sufficient routing 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?

Beyond the readOnly/idempotent annotations, the description explains meaningful behavioral context: the warehouse is 'only a DAILY snapshot', Last_Load is 'the only reliable data is fresh signal', and Backup_Taken defines accuracy bounds. It also warns against presenting day-old data as current, which is valuable operational nuance.

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 well-structured and each sentence adds value: object identity, field semantics, usage scenarios, cautionary guidance, and a pointer to further documentation. It is information-dense without padding.

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, read-only, output schema present), the description fully covers what an agent needs to decide when to call it and how to interpret its results. It even includes a pointer to the broader model guide for additional 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?

The tool has zero parameters, so the schema provides no constraints. The description explicitly states 'No parameters', which is sufficient for the agent; no additional parameter semantics are needed.

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 states a specific verb and resource: 'Return the warehouse freshness markers from the special object warehouse_last_load'. It clearly differentiates the tool from siblings by explicitly noting the object is 'NOT a wh_ view and does NOT appear in list_views', making its unique role unmistakable.

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 gives clear when-to-use guidance: 'Use it to check how current the data is, and as the first smoke test after deploy' and advises checking it first for time-critical questions. It does not explicitly name an alternative tool like query for row-level data, but the priority and purpose are well stated.

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 cover read-only, idempotent, non-destructive behavior, so the description earns credit for added context: live INFORMATION_SCHEMA with a snapshot fallback, the 'source' field indicating which, and the missing wh_ticket trap. This is useful behavioral detail beyond what structured fields provide.

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 dense but every sentence earns its place: purpose, first-use workflow, fallback behavior, trap, filter, and a pointer to the guide. It is front-loaded with the most important discovery intent before diving into caveats.

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?

Completeness is high for a read-only discovery tool with an output schema: it explains the discovery workflow, the fallback source, the filtering option, the critical missing-view trap, and how to resolve IDs. Nothing needed to call it correctly is left out.

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 the baseline is 3. The description says the filter is optional and case-insensitive and matches view names, but the schema already documents this plus an example, so the description adds no substantial new parameter 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?

States a specific verb 'List' plus the exact resource ('Autotask Data Warehouse views') and scope ('all named wh_*') and the key output ('column counts'). It clearly differentiates from siblings by mapping the subsequent steps to describe_view and query.

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?

Explicitly instructs 'Use this FIRST to discover which view holds the data you need, then describe_view for its columns and query to read rows', giving the agent a clear workflow over sibling tools. The trap about wh_ticket living in wh_task also steers the agent away from a common wrong lookup.

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 true and destructiveHint false, and the description adds substantial behavioral detail: the read-only guard rejects a long list of statement types, max_rows is hard-capped at 500, truncated=true signals incomplete results, the warehouse is a daily snapshot, and money columns return as decimal strings. Nothing contradicts the annotations, and the added context is critical for correct use.

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 long but every sentence carries operational weight—there is no filler. It front-loads the core purpose and constraint, then layers on traps, freshness, and glossary guidance in a logical order. This density is appropriate for the tool's complexity.

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 SQL execution tool with an output schema, constraints, and many warehouse-specific pitfalls, this definition is exceptionally complete: it covers statement validation, row caps, truncation semantics, data freshness, ID resolution, and business-term definitions. An agent can use this tool correctly with minimal need for additional documentation beyond the referenced guide.

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?

With 100% schema coverage the baseline is 3, but the description heavily enriches both parameters: it specifies exactly which SQL constructs are allowed/rejected, explains how to respond to truncated=true (narrow query, aggregate, or raise max_rows), and warns about non-obvious ID columns and join keys. This adds meaning far beyond the schema's one-line descriptions.

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 a specific verb and resource: 'Execute EXACTLY ONE read-only SQL statement against the Autotask Report Data Warehouse and return its columns and rows.' It clearly distinguishes the tool from siblings like list_views and describe_view by scoping it to query execution rather than schema exploration. The read-only and single-statement constraints further pin down the purpose.

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 gives clear context for use (read-only SQL against the warehouse) and explicitly names an alternative path for freshness: 'call last_load and state the load time, or use the live Autotask source instead.' It also directs the agent to read warehouse://guide before writing queries. However, it does not explicitly contrast against list_views/describe_view for schema discovery, so it stops short of a full when-not-to-use map.

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