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

Annotations only cover the read-only/idempotent/open-world profile, but the description goes well beyond: it enumerates the verdict taxonomy, explains that blocked packages carry `tracking` links, and discloses that tracking costs one GitHub search per repo, uses GITHUB_TOKEN, and never changes a verdict. It also spells out index resolution precedence (index_url vs. requirements-file -i vs. PIP_INDEX_URL vs. PyPI).

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 is front-loaded in the first clause, followed by input-source mechanics and a compact status glossary. The status list is dense but each term is needed to interpret output; no filler sentences. Slightly long single breath, but structured.

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 carries return-value burden and does so reasonably: verdict semantics and the `packages[].tracking` field are explained, along with the bump outcome. What's less explicit is the shape of the per-package record (current version, bump target, platform coverage), which an agent would need to consume results fully.

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 adds real meaning the schema lacks by naming the exact lockfile formats read from `path` (uv.lock, pylock.toml, poetry.lock, Pipfile.lock, requirements.txt, pyproject.toml). It still leaves `glibc`/`macos` and the platform set entirely to the schema, which 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?

The first sentence gives a specific verb, resource, and trigger ('Before moving a project to a new Python... list every dependency that has no installable wheel for it'), plus the concrete output ('smallest version bump'). It does not name or differentiate against the sibling explain_wheel, so it falls short of the top band.

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 trigger condition is explicit ('Before moving a project to a new Python (e.g. 3.15 or free-threaded 3.15t)'), and the description clarifies the two input modes: read lockfiles from `path`, or check explicit `requirements` specs. It stops short of stating when to use explain_wheel instead, so no full routing 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?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds the useful behavioral detail that the verdict is derived from PEP 425/600/656/803 tag rules, which explains how the answer is computed, but it does not say what the response looks like or how tag mismatches are reported.

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 dense, front-loaded sentence with a helpful inline example; nothing extraneous. It is slightly packed with PEP citations, but 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?

With no output schema, an agent learns the tool returns an install/no-install verdict for a given filename, python, and platform set. The example filename and PEP references give enough grounding to call it correctly, though the exact return shape and mismatch explanation remain unstated.

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 67%, and the schema already documents the python and platforms parameters with defaults. The description only echoes that the target is CPython plus platforms and adds no format or edge-case detail (e.g. free-threaded 't' variants) beyond the schema text, so it neither compensates further nor regresses.

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 ('say whether ... installs'), the resource (a wheel filename), and scope (target CPython and platforms), backed by a concrete example and the governing PEP references. It is clearly a compatibility-check tool and distinguishable from the sibling check_python_upgrade.

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 implies the use case (checking install compatibility before attempting an install) but never states when to pick this over the sibling tool or what prerequisites exist. No exclusions or alternative routing are given, leaving usage inference to the agent.

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