jev-guide

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

Annotations already declare readOnlyHint=true, so the safety profile is covered and the bar for the description is lower. The description adds that the output is the 'exact configuration' for a gateway, but says nothing about the form of that config (snippet, file contents, command) or any auth prerequisite. With no output schema, more behavioral detail would help.

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; the purpose comes first and the usage trigger second. 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 tool whose whole job is returning a configuration artifact, the description never specifies what that artifact looks like (raw JSON, CLI commands, a file path) and there is no output schema to compensate. It is adequate to select the tool but leaves a real gap about the return value.

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 client, key and url. The description merely restates the client enum values ('Claude Code, Codex or Cursor') and adds no meaning about the key or url parameters beyond what the schema provides. 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 ('Returns') and resource ('the exact configuration') with the concrete scope of pointing Claude Code, Codex or Cursor at a JEV gateway. However, it does not differentiate itself from the close sibling get_mcp_install_commands, which an agent could easily confuse with this tool.

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 an explicit trigger: 'Use when a user asks how to connect a coding agent to JEV.' That is a clear when-to-use condition. It stops short of any exclusion or alternative routing (e.g., when to prefer get_mcp_install_commands), so it doesn't reach the top band.

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 is consistent with a command-generating tool, and the description usefully adds that output spans three clients plus a Cursor one-click link. Beyond that it discloses no auth requirements, rate limits, or whether commands are pre-validated, so with annotations already carrying the safety profile this is adequate rather than rich.

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, zero filler, with the what-it-returns detail front-loaded before the usage trigger. 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?

A simple read-only tool with a fully documented two-param schema and no output schema; the description broadly characterizes the return value (commands per client plus a link). Nothing essential is missing, though it could note the expected output shape more concretely.

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 (url, name) are already documented with examples and format hints. The description adds no additional parameter semantics, making the baseline 3 correct 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 (Returns) and resource (install commands for a remote MCP server) and enumerates the target clients (Claude Code, Codex, Cursor). It does not explicitly distinguish itself from the sibling get_client_setup, which could plausibly be confused with this, 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?

"Use when a user wants to add an MCP server URL to their agents" gives clear triggering context. It offers no explicit exclusions or named alternatives (e.g. when to prefer get_client_setup), so it is not 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?

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds that each entry explains what the model does, but discloses nothing beyond that (no ordering, caching, or response shape), which is acceptable for a trivial zero-param 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 short sentences, zero waste, with the identity of the tool front-loaded and the usage hint second.

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 carries the burden and does state the return content (names plus what each does). Nothing essential is missing for calling this 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?

The tool takes zero parameters, so there is nothing to document; the baseline for a parameterless tool 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 specific verb and resource ('Lists the JEV model names') and even names concrete examples (jev-auto, jev-fast) plus what the list contains. It doesn't explicitly contrast with the setup/install siblings, but its purpose is 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?

Gives a clear triggering condition: 'Use when choosing which model name to configure.' No alternatives or when-not guidance are offered, but the usage context is explicit and actionable.

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 tells the agent this is a safe read, and the description usefully frames it as a predictive/simulation call ('would pick') rather than an action. It adds no detail on rate limits, output shape, or whether the prompt is stored, which is minor for a pure-read classifier.

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 short sentences, purpose front-loaded, no filler. Every clause contributes either what it does or when to use it.

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-only tool with no output schema, the description covers the essentials: what is classified and what is returned (task class and model tier). It could state the output format or whether this is a dry-run that never dispatches, but the gap is small.

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 there is a single well-documented parameter, so the schema carries the load. The description adds marginal meaning by scoping the input to a 'coding prompt', implying non-coding prompts are out of domain, but nothing beyond that.

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 names a specific verb ('Shows') and a concrete resource ('which task class and model tier the jev-auto router would pick'), so the agent knows exactly what it returns. It is clearly distinct from siblings like list_model_aliases or get_client_setup, though it never names them explicitly.

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 a use case ('to explain or predict routing decisions') which implies when the tool is appropriate. However, there are no exclusions, no prerequisites, and no comparison against the sibling tools that could plausibly be confused with it.

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