Faucet

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

Annotations only supply readOnlyHint=false, so the description usefully adds three behavioral facts: the mandatory filter guards against full-table deletes, the call returns a count of deleted records, and DELETE permission on the table is required. That is meaningful auth and safety context beyond the annotation, though reversibility/transaction behavior is unstated.

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 adding distinct information (action, safety constraint, return value, permission requirement) with the core purpose front-loaded. 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?

For a destructive three-parameter tool with no output schema, the description covers the safety guard, the return value, and the required permission, leaving nothing an agent needs in order 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?

Schema description coverage is 100%, so all three parameters are already documented with an example filter expression; the description adds only the rationale for why filter is mandatory. This is the expected baseline when the schema carries parameter detail.

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 (Delete) and resource (records from a database table) plus the matching condition, which cleanly separates it from siblings like faucet_insert, faucet_update, and faucet_query without opening a 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?

The description imposes a hard constraint ('a filter is required') that implies usage, but never states when to choose faucet_delete over faucet_raw_sql or faucet_update, nor any exclusions. Guidance is 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?

readOnlyHint=true already signals a safe read, and the description usefully adds the authorization requirement (GET permission on the table's schema). It goes beyond the annotation with an access constraint, though it does not discuss rate limits or result size 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?

Three tight clauses: what is returned, when to use it, and the permission requirement. The return contents are front-loaded and every sentence carries distinct information 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 no output schema, the description compensates by spelling out the return contents (columns, keys, indexes), and it also covers the permission prerequisite. For a two-parameter read-only tool this is sufficient for an agent 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?

Schema description coverage is 100%, so both parameters (service, table) are already documented in the schema. The description adds no format, naming, or lookup detail beyond what the schema provides, which is the expected baseline when structured fields do the work.

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 (Get) and resource (detailed schema for a specific table) and enumerates exactly what is returned: columns, types, nullability, defaults, primary keys, foreign keys, and indexes. This clearly separates it from siblings like faucet_list_tables (enumerates tables) and faucet_query (runs queries).

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 concrete usage context: 'Use this to understand table structure before writing queries.' That orients the agent well, but it names no alternative or exclusion condition (e.g., when to prefer faucet_list_tables or faucet_raw_sql), so it stops short of explicit routing.

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 only declare readOnlyHint=false, a thin safety signal. The description adds real behavioral context beyond that: the record payload shape, that returned rows include auto-generated fields only when the database supports RETURNING, and the POST permission requirement. Error/conflict behavior is still unstated.

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, front-loaded with the core action, with the payload format, return behavior and permission caveat each earning their place. No redundancy or 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 no output schema, the description usefully covers return-value behavior (RETURNING) and the permission prerequisite, and all three parameters are documented by the schema. Missing only failure/conflict semantics, which is tolerable here.

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 the baseline is 3. The description goes slightly beyond the schema by explaining that each record maps column names to values, clarifying the semantics of the 'records' array beyond the schema's example.

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 (insert), resource (database table) and scope (one or more records), which is unambiguous next to siblings like faucet_update, faucet_delete and faucet_query. It does not, however, explicitly name or route against any sibling, so it stops short of a 5.

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 tool's purpose implies its use (add rows to a table), and one prerequisite is stated ('Requires POST permission on the table'). But there is no guidance on when to prefer this over faucet_raw_sql or faucet_update, and no exclusions are given.

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=true, so the safety profile is covered. The description adds real context beyond that: the exact shape of each returned record and the role-based access filter ('Only services your role has access to are listed'), which tells the agent results may be silently scoped. It omits pagination/empty-result behavior, so not 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?

Three short sentences, front-loaded with the action, then return shape, then usage order. Every sentence carries information an agent needs; nothing is 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?

There is no output schema, and the description compensates by naming the returned fields (name, driver type, active status, access mode). Combined with the zero-parameter schema and readOnly annotation, an agent has everything needed to call this 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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-level gaps are possible here.

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 ('List all database services configured in Faucet') and enumerates the fields returned, which lets an agent distinguish it from faucet_list_tables and faucet_query without opening a schema. The resource scope is unambiguous.

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 this first to discover available databases before querying' gives explicit sequencing relative to the query tools, which is genuine when-to-use guidance. It stops short of naming the closest alternative (faucet_list_tables) or stating when not to use it, so it is clear but not complete.

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 only declare readOnlyHint=true, so the description adds meaningful value by disclosing the permission requirement ('Requires GET permission on _table') and the approximate nature of row counts. That is well beyond structured data. It stops short of 5 because it doesn't describe pagination behavior, scope limits, or what happens with large schemas.

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 tight sentences: what it returns, when to use it, and the permission requirement. Nothing is wasted and the payload (what you get back) 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?

For a read-only, single-parameter listing tool with no output schema, the description covers purpose, usage context, return contents, and auth needs. The only gap is the absence of pagination or volume guidance, which is minor but real for a 'list all tables' operation.

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 single 'service' parameter is fully described in the schema as the database service to list tables for. The description adds no syntax, format, or lookup guidance beyond that, so baseline 3 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?

States a specific verb and resource ('List all tables in a database service') and distinguishes itself from siblings like faucet_describe_table and faucet_query by promising row counts and column summaries. An agent can immediately tell what data comes back.

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 clear context: 'Use this to explore what data is available before querying specific tables.' That is a real when-to-use signal pointing at faucet_query as the downstream step. It does not name explicit alternatives or exclusions, so it stops short of a 5.

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?

The readOnlyHint=true annotation is consistent with the read semantics. The description goes beyond it by disclosing the authorization requirement (GET permission on the table) and the response format (JSON), plus default/max record behavior via the schema. It does not cover things like row-limit enforcement errors or pagination end conditions, but it adds real context over the annotation.

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?

Purpose and permission requirement are front-loaded, followed by an efficiently bulleted syntax reference. The length is justified by the query-language surface area, though the filter example list is somewhat padded with overlapping comparison forms.

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 an 8-parameter query tool with no output schema, the description covers return format, auth needs, and both filter and order grammars, which is most of what an agent needs. The main gap is the absence of any statement about limitations relative to faucet_raw_sql (joins, subqueries) and about pagination behavior such as limit/offset interaction.

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 the baseline is 3, but the description adds materially useful semantics: a full DreamFactory-compatible filter operator reference (comparisons, AND/OR, IN, LIKE, IS NOT NULL, BETWEEN, CONTAINS) and order-clause syntax. That enriches 'filter' and 'order' well beyond the schema's single-line examples.

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+resource ("Query records from a database table") and enumerates its supported capabilities: filtering, field selection, ordering, pagination, JSON output. An agent can readily distinguish this from faucet_insert/delete/update. It stops short of naming a sibling (e.g. faucet_raw_sql) for advanced cases, so it is clear but not fully differentiated.

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?

"Requires GET permission on the table" is a genuinely useful precondition for deciding whether to call it. Otherwise there is no explicit when-to-use/when-not-to-use guidance and no routing to alternatives such as faucet_raw_sql for complex or join-style queries. Usage is implied by the read-oriented verb rather than 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 only give readOnlyHint=false, but the description adds substantial context beyond that: the RBAC requirement (role rule granting all verbs on _sql), the as-is execution semantics, the refusal on read_only services, and the placeholder syntax per dialect. This is rich behavioral disclosure the annotations do not cover.

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-loaded with purpose and availability, then permissions, then execution semantics and parameter syntax. Every sentence earns its place with only minor density in the middle clause about role rules.

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?

Complete for a dangerous arbitrary-SQL tool: availability gate, permission requirement, mutation warning, and dialect-specific parameter syntax are all covered. A mention of return shape would help, but no output schema exists and the query-result nature is inferable.

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 the schema already documents all five parameters. The description adds useful detail on params syntax ($1 vs ?) that goes beyond the schema's generic 'Positional parameters' text, but does not cover limit or timeout nuances.

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+resource ('Execute a raw SQL query') and immediately scopes when it applies ('Only available for services with raw_sql_allowed enabled'). This clearly distinguishes it from siblings like faucet_query and faucet_insert, which are narrower typed 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?

Explicitly names the alternative tool to check availability ('Use faucet_list_services to check which services allow raw SQL') and states the exclusion condition (refused on read_only services). When-to-use and when-not-to-use are both present.

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 only readOnlyHint=false provided, the description adds real behavioral context: the filter is mandatory specifically to prevent accidental full-table updates, and PATCH permission on the table is required. These are destructive-safety and auth details the annotation does not convey.

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 tight sentences with the core action, the record semantics, the safety constraint, and the permission requirement front-loaded. No filler, though the record clause is mildly redundant with the schema.

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 mutation tool with no output schema, the description covers what it does, the mandatory filter safeguard, and the required permission. It omits any return-value expectation or confirmation behavior, but nothing critical to invoking it correctly 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 description coverage is 100%, so the schema already documents all four parameters. The description reinforces that record holds column values to set and that filter selects the target rows, but adds no syntax or format details beyond the schema, so 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 clear verb (update) and resource (records in a database table matching a filter), which distinguishes it from faucet_insert and faucet_delete. It does not explicitly name a sibling or draw the line against faucet_raw_sql, so it stops short of a 5.

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 names a safety constraint (filter required) and a permission prerequisite, but never says when to choose this over faucet_raw_sql, faucet_query, or faucet_insert. There is no when-not guidance and no alternative routing, leaving usage largely to inference.

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