gitmanual

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered structurally. What the description adds beyond that is provenance — 'facts come from the repo's own files, not guesses' — which usefully signals reliability and the possibility of 'unknown' answers. It says nothing about cost, latency, or how much of a large repo is scanned, so the addition is real but modest.

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 long sentence, but it is front-loaded with the core verb-and-resource framing and the enumerated clauses each add distinct information about the return payload. The trailing 'not guesses' clause is a slight stylistic flourish but also conveys a meaningful guarantee.

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?

No output schema exists, so the description must describe the return value itself — and it does so thoroughly, covering compatibility verdicts, download artifacts, command lists, and source-build steps. The one gap is the absence of any guidance relative to the sibling tool, which is a routing concern more than a completeness one.

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%, and every parameter (repo, os, arch) already has enum values or an explanatory description, so the schema carries the semantics. The description's mention of macOS/Windows/Linux and 'ready-made downloads' loosely echoes the os and arch filters but never states that passing them narrows the output. 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?

The description names the resource (a GitHub repository) and enumerates concretely what the result contains: OS compatibility with reasons, ready-made downloads, install commands from the README, required parts, and from-source steps. An agent knows exactly what it gets back. It stops short of naming the sibling get_setup_script, so the boundary between the 'manual' and the 'script' is left implicit.

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 explicit when-to-use statement, no exclusion, and no reference to the alternative get_setup_script despite that sibling existing. The purpose implies the use case (understanding how to install a repo), but the agent must infer whether it wants this narrative answer or the sibling's executable script.

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 and openWorldHint, but the description adds real behavioral detail about the generated artifact: it stops at the first error, skips already-installed components, and never starts servers. That tells an agent what the script will and won't do when later executed. It doesn't cover authentication requirements or how the script body is returned.

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 no filler. The core deliverable is front-loaded, followed by behavioral constraints and the user-review instruction in logical order.

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 two-parameter read-only tool with no output schema, this covers purpose, OS mapping, execution semantics, and handling guidance. The only omission is how the script text is returned, a minor gap against the annotation coverage.

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 50%: the repo parameter is documented in the schema, but the os enum values carry no descriptions there. The description compensates by mapping each OS to its script flavor (bash vs PowerShell), which adds meaning beyond the bare enum. That fills the main coverage gap.

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 deliverable: a single setup script for the repo, tailored per OS (bash on macOS/Linux, PowerShell on Windows). An agent can tell it produces a script rather than executing setup. It stops short of naming the sibling get_setup_manual to sharpen the distinction.

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 post-retrieval usage rule ('Show it to the user to read before running it'), which is useful context for how to handle the result. But there is no explicit guidance on when to choose this over get_setup_manual, leaving the alternative to inference from the names alone.

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