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

The description contains 'Read-shaped tools only (anything that buys, sells or writes refuses),' implying this tool is read-shaped (read-only). Yet the annotation declares readOnlyHint: false, meaning the tool is not strictly read-only and may have side effects. This is a direct contradiction, and the description does not clarify the actual side-effect profile beyond saying 'in-memory'.

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?

The first sentence is useful, but the description quickly devolves into server context ('a live seat on The Wall'), irrelevant read-shaped tool policy, and a listing URL. This wastes the agent's attention and does not front-load the most actionable information about how to call the tool.

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 is provided, and the description gives no indication of what the tool returns beyond 'their data comes back as it is' (vague). With 4 parameters, nested objects, and complex input requirements, the description does not provide enough information for the agent to correctly compose the manifest or interpret results.

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?

With schema description coverage at 0%, the description must explain parameter meaning. It clarifies that skillIds are 'exact skill IDs already chosen' but gives no guidance on profile, name, or targets. The nested profile object has required goals and optional fields that are entirely unexplained, so an agent cannot reliably construct valid 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?

The description states a specific verb and resource: 'Build an in-memory Core manifest from exact skill IDs already chosen by Codex or Claude.' This clearly identifies what the tool does and hints at its input (skill IDs) but does not actively differentiate from sibling tools like inspect_stack or diff_stack beyond the 'already chosen' phrase.

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?

Provides a sequencing precondition: 'Call only after the agent has enumerated primary project capabilities.' However, it gives no guidance on when to choose this over siblings (e.g., inspect_stack, diff_stack) or when not to use it. No alternative tools are mentioned, so the usage context is partial.

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