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

No annotations are provided, so the description carries the full burden. It usefully discloses that data is read from INFORMATION_SCHEMA / sys catalog views, which implies a read-only, metadata-only operation, and it warns of a table allowlist that may restrict access. But it doesn't state whether it returns empty or errors on a nonexistent table, so transparency is partial.

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?

Front-loads the core purpose, then the detail of what is returned, then the naming convention, then the allowlist caveat. Three compact sentences, no filler, every clause 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 single-parameter, metadata-read tool with no output schema and no annotations, the description covers purpose, return contents, input format, and the allowlist precondition. What's missing is edge-case behavior (nonexistent table, allowlist rejection), which an agent would want but isn't essential to invoke the tool 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?

Schema coverage is 100% and the sole parameter already documents the schema-qualified format. The description reinforces this by explicitly accepting both "Table" and "schema.Table", which adds a small amount of practical clarity beyond the schema. With one parameter, baseline is 4.

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 (Describe) and resource (a table), and enumerates exactly what is returned: columns with sub-attributes, primary key, foreign keys, indexes. An agent can distinguish this from list_tables (enumeration) and sample_rows (data preview) without opening any schema.

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 the nature of the tool — you describe a table to learn its structure before querying. However, the description never explicitly says when to reach for this versus list_tables (to find a table) or verify_connection (to check connectivity). The allowlist note hints at a precondition but is not framed as guidance.

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 carries the full behavioral burden and does well: it discloses that row counts are approximate and sourced from sys.partitions with no COUNT(*) executed, which is a real performance trait an agent should know, and it discloses allowlist filtering that can silently reduce results. It stops short of stating read-only/pagination behavior explicitly, but 'List' plus 'no COUNT(*) is executed' conveys a safe, cheap read.

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 with zero filler, front-loaded with what is returned before the metadata caveat and the allowlist caveat. Every clause adds 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?

There is no output schema, so the description must describe returns — and it does, naming the identifier format and the row-count caveat. Combined with the allowlist note, an agent has everything needed to call this zero-parameter tool correctly and interpret the result.

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 takes zero parameters, so the baseline is 4. The description correctly adds no parameter detail and instead spends its words on output semantics, which is the right allocation.

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 precise verb and resource ('List all tables in the database') and goes further by specifying the exact return shape ('as schema.table with approximate row counts'). This clearly separates it from siblings like describe_table (single table) and run_query (arbitrary SQL), which is a meaningful distinction an agent can act on.

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 rather than stated: the agent can infer this is the discovery tool to call before describe_table or sample_rows, but no explicit when-to-use or when-not-to-use guidance is given. It never names an alternative or a condition that would select it over run_query.

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 carries the full burden and does so: it discloses validation order, the destructive-operation prohibition, the allowlist restriction, MAX_ROWS truncation surfaced via a 'truncated' flag, a query timeout, and that rejections name the violated rule. These are exactly the behavioral traits an agent needs before invoking.

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 sentences, each carrying distinct information (what it runs, how it's validated, what limits apply and how errors surface). Front-loaded with the core action and free of 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?

For a single-parameter read tool with no output schema, the description covers the safety profile, execution limits, truncation signaling, and error behavior. An agent has everything needed to call it correctly and interpret the result.

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 is only one parameter and schema coverage is 100%, so the schema already documents the SQL string. The description reinforces that it must be a single SELECT (CTE allowed) but adds no syntax or formatting detail beyond the schema, matching the baseline for full-coverage params.

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 (execute a read-only SELECT against the database) and marks scope (single statement, WITH/CTE supported). It is clearly distinguishable from the list/describe/sample siblings, which are narrower introspection tools.

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 validation rules (exactly one statement, SELECT-only, no write/exec keywords, optional allowlist) tell the agent what is acceptable input and imply when this tool is the right choice versus the narrow siblings. It stops short of explicitly naming those siblings or stating when to prefer them, so it is clear context rather than full routing guidance.

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 carries the burden and does add value: it discloses the cap (max 50), the default, and that the call is 'subject to the table allowlist if configured' — a real access constraint not in the schema. It omits error behavior for non-allowlisted tables, but the safety profile (read-only inspection) is clear from the wording.

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: the row limit is front-loaded, then the naming format, then the allowlist caveat. No filler and every clause carries 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?

There is no output schema or annotation, but for a simple sampling tool the description conveys the return shape (first N rows) and the key constraints. A note on behavior when the table is not allowlisted or does not exist would close the remaining gap.

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 both parameters are already documented. The description's mention of the default (5) and maximum (50) and the 'Table' or 'schema.Table' format largely repeats what the schema descriptions already say, adding no syntax or behavioral detail beyond it.

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 ('Return the first N rows of a table') plus the intent ('to inspect its content'), which distinguishes it from list_tables and describe_table. It does not explicitly contrast with run_query, which could also return rows, so the sibling differentiation is only implied.

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?

'To inspect its content' implies a quick-peek use case versus a full query, giving some usage context. However, it never states when to prefer run_query instead, nor any exclusions, so the guidance remains implied rather than explicit.

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 carries the full behavioral burden. It usefully discloses the internal check set and the reported outcome, and the absence of parameters implies a safe, non-mutating probe. However, it does not state failure behavior (exception vs. reported failure), idempotency, or required permissions for the verification itself.

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 filler, with the reported content front-loaded and the usage trigger placed last. Every clause 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?

There is no output schema, so the description correctly takes on explaining the return content (checks run, pass/fail, detected privileges), which it does well. It stops short of describing error/failure modes or what to do after a failed verification, a minor gap for a diagnostic 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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. No parameter-related confusion is possible.

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 (verify the database connection) and precisely enumerates what is reported: which checks ran (server roles, database roles, effective permissions), which passed, and any detected write privileges. This clearly distinguishes it from the sibling data-access tools (list_tables, describe_table, sample_rows, run_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?

It gives an explicit trigger: 'Use this to diagnose why the server refuses to expose query tools.' That is a clear when-to-use condition. It does not name or exclude alternatives explicitly, but the sibling set makes the boundary obvious.

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