skgate

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

Annotations already cover readOnly/idempotent/closed-world safety, but the description adds genuinely new context: 'Read-only and offline: it answers from the binary alone and contacts nothing' clarifies there is no network dependency or side effect. It also enumerates the returned fields, though the output schema already documents the shape.

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 the verb and scope, followed by argument behavior, return shape, and the routing hint. Three tight sentences 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?

Given a zero-param tool with full schema coverage, existing annotations, and an output schema, the description supplies everything else an agent needs: what it answers, that it is offline/read-only, and when to call it relative to siblings.

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?

Zero parameters, so per calibration the baseline is 4. The description confirms 'Takes no arguments', which matches the empty schema and removes any ambiguity about hidden inputs.

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 ('Describe skgate') and enumerates exactly what it covers: what it is, running version, edition, licence, source and docs locations. An agent can distinguish it from list_features and config_help (both named) 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?

Explicitly instructs 'Call it first to learn what skgate is before using list_features or config_help', naming both alternatives and the ordering condition that selects this tool. No inference required.

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, and the description adds real value beyond them: defaults are documented README values, no secret is ever included, result ordering follows the README table, unknown-name errors enumerate valid names, and it reads no environment variable at all. That is exactly the kind of edge-case disclosure annotations cannot carry.

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?

Roughly four dense sentences, front-loaded with purpose and scope, then error behavior, then the read-only/offline caveat. No filler; each clause carries a distinct fact an 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?

A one-parameter read tool with full annotation coverage and an output schema, yet the description still describes the returned shape (settings array of name/default/description), the ordering, and the error path. Nothing needed to call 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 coverage is 100%, so the baseline is 3, and the description adds genuine semantics on top: the name is an exact match and case-insensitive, and omission returns the full set. The case-insensitivity point in particular is not derivable from the schema, which implies a strict-exact match.

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: 'Explain the environment variables that configure a skgate server.' The scope is narrow enough that an agent can separate it from siblings like 'about' and 'list_features' without opening the schema, and it explicitly names the optional target (a variable name).

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 states the selection condition clearly: pass an exact variable name to narrow scope, omit it to get everything, and an unknown name raises an error listing valid names. It also gives an implicit 'when not to use' by noting it cannot report values from a running server. It does not, however, name any sibling tool as the alternative for live server values.

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, openWorldHint=false and destructiveHint=false, so "Read-only and offline" is largely redundant. The description does add non-obvious behavior beyond the annotations: the error semantics for an unrecognized area and the exact shape of the returned object.

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 the core purpose and the default behavior ("Without an area it returns every feature"), then the return shape, then the error case. Dense but every sentence carries information; the enum parenthetical is long but 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?

An output schema exists so return values need not be spelled out, yet the description still summarizes them, and it covers the default, the enum meanings, and the error path. For a zero-required-parameter read tool this is essentially complete, with only sibling disambiguation 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 enum is already documented, but the description goes further by explaining what each enum value actually covers (mcp = MCP servers and tools, llm_proxy = OpenAI-compatible API, providers, aliases and keys, etc.). That is real added meaning an agent cannot get from the schema alone.

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 what skgate does, one entry per feature") and immediately scopes it with the optional area filter. It is clear what the tool returns, but it never distinguishes itself from the sibling tools 'about' and 'config_help', which plausibly also describe product information.

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 when-to-use guidance for the one decision point: omit the area to get everything, pass an area to narrow. It also documents the failure mode (unknown area is an error naming valid values). It stops short of routing the agent away from the overlapping siblings about/config_help.

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