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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not that this is a read-only operation, not permission/privilege requirements (relevant given it reports grants), and not the shape or size of the result. For an introspection tool with zero annotation coverage this is a serious gap.

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?

It is short, but brevity here reflects under-specification rather than conciseness; it is a sentence fragment with no verb and no structure to front-load. Nothing is wasted, but nothing earns its place either.

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 no annotations, no output schema, and an undocumented parameter, the description is the only source of information and it omits the operation itself, its safety profile, its defaults, and its return content. An agent cannot reliably invoke this tool from what is given.

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 'schema' parameter has 0% schema description coverage and a default of 'public' that the description never mentions. The phrase 'in a schema' only loosely gestures at the parameter and provides no format, default behavior, or fallback semantics.

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 is a noun phrase ('Tables, views, columns, grants and functions in a schema') with no verb, so it never states that the tool retrieves or introspects anything. It adds the list of returned object types beyond the bare name get_schema, but an agent must infer the action entirely. It also does not distinguish this tool from siblings like run_audit_query or scan_repo.

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?

There is no when-to-use guidance, no mention of when an agent should prefer this over run_audit_query or scan_repo, and no prerequisites. The only hint of context is the phrase 'in a schema', which is not actionable 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 burden. It usefully discloses the transport (PostgREST) and that only a row count is returned, not the rows themselves, which tells the agent this is a read-only existence/visibility probe. However it says nothing about side effects, failure semantics, permissions required to run the probe, rate limits, or what a denial returns.

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?

A single tight sentence that front-loads the action and scoping constraint ('row count only') with no wasted words. Well sized for a two-parameter probe.

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 probe with no output schema and no annotations, the core purpose is conveyed, but the undocumented 'op' parameter and the absence of any usage/alternative context leave gaps. It is adequate but not complete for correct invocation.

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 0%, so the description should compensate, but it adds meaning only for the 'table' parameter (implicitly the target). The 'op' parameter, which defaults to 'select', is never mentioned in the description, leaving its allowed values and impact undocumented anywhere the agent can see.

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 (check/probe) and resource (whether the anon key can read a table), with the mechanism (PostgREST) named. This is distinguishable from siblings like run_audit_query or get_schema, though it doesn't explicitly contrast itself with them.

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 versus run_audit_query or get_schema, and no stated prerequisites. Usage is only implied by the phrase 'whether the anon key can read a table', which suggests an access-control/RLS probe but leaves the triggering condition 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?

No annotations are provided, so the description carries the full burden. It implies a read-only audit operation via 'audit query' and reveals the allowlist constraint, but says nothing about required permissions, behavior on an invalid or non-allowlisted query_id, cost/runtime, or side effects.

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?

A single front-loaded sentence with no filler; the scope constraint is stated immediately. It is efficient, though its brevity leaves real gaps that are penalized under other dimensions rather than here.

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?

Because an output schema exists, return values need not be described. However, for a single-parameter tool whose only parameter is unconstrained in schema, the definition should have enumerated or referenced the accepted query_id values more concretely, and given at least a hint of usage context relative to the other tools.

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 0% and query_id has no title/description beyond its name, so the schema contributes nothing. The description partially compensates by pointing to Q1..Q20 in audit-queries.md, but it does not state the accepted literal format (e.g. 'Q1' vs '1') or that the values form an enumerable set, leaving the agent to guess valid values.

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 (run) and resource (audit query) with an explicit scope constraint: allowlisted queries Q1..Q20. An agent immediately knows this executes a predefined audit query rather than an arbitrary one. It does not explicitly differentiate from the sibling tools, but those (get_schema, probe_as_anon, scan_repo) share no surface ambiguity.

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 constrains inputs to the allowlist but never says when this tool should be chosen over siblings like scan_repo or get_schema, nor when an audit query is the right approach versus a direct schema read. No exclusions or prerequisites are 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?

With no annotations, the description carries the full behavioral burden, and it does disclose one genuinely useful trait: results are 'locations only', so secret values are not returned. It says nothing about required permissions, whether the scan is read-only, runtime cost, or repo configuration assumptions.

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?

A single tight sentence with the target class front-loaded and the important output caveat attached inline. Every clause earns its place and there is no 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?

An output schema exists and the tool has no parameters, so return-value and argument explanation are not needed. The main remaining gap is behavioral context (permissions, read-only nature, which repo is 'configured'), which is thin but not fatal for a no-arg scan.

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 clarify beyond what the empty schema already conveys. Baseline 4 applies for a 0-parameter tool.

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 (Scan) and resource (the configured repo) plus the exact target class (exposed service-role keys / JWT secrets). It implicitly separates itself from siblings like run_audit_query and probe_as_anon, but never names an alternative explicitly, so sibling differentiation is only inferred.

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?

There is no guidance on when to reach for this tool versus run_audit_query, probe_as_anon, or get_schema. The parenthetical '(locations only)' scopes the output but does not tell an agent when the tool is appropriate or what prerequisites must hold.

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