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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it is safe and idempotent. The description adds value by stating that Core 'verifies catalog membership and preserves the selection without ranking, substitution, policy, or metadata filtering,' and explicitly notes that the 128-skill cap is a technical limit, not a semantic policy. This provides behavioral nuance beyond the annotations without contradicting them.

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 description is moderately sized and well-structured. It leads with the core purpose, then provides a precondition, then clarifies behavioral semantics. Every sentence serves a function—no filler. While not ultra-terse, it is appropriate for the tool's complexity and reads clearly.

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 the tool's complexity (nested profile object, optional targets, name) and zero schema parameter descriptions, the description is incomplete. It explains the composition action but omits details on how profile and targets are used, what happens on invalid skill IDs, error handling, or the structure of the resulting manifest. It does not mention output format (no output schema), so the agent lacks critical context for correct invocation and result interpretation.

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 0%, so the description must compensate for the lack of parameter documentation. However, it only mentions 'exact skill IDs' (skillIds) and does not explain profile, targets, or name. The nested profile object with goals, languages, frameworks, constraints, and projectType is left entirely undocumented. The description fails to clarify how these parameters influence the manifest construction, making it difficult for an agent to construct a correct call.

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 opens with a precise verb and resource: 'Build an in-memory Core manifest from exact skill IDs already chosen by Codex or Claude.' This clearly distinguishes it from siblings like search_skills (discovery), inspect_stack (inspection), and diff_stack (comparison). The purpose is unambiguous and specific.

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 an explicit precondition: 'Call only after the agent has enumerated primary project capabilities, searched and compared candidates for each...' This tells the agent when it is appropriate to invoke. It does not explicitly name alternative tools for different situations, but the precondition effectively gates usage and aligns with the pipeline context. The clarification about the 128-skill limit and no policy also guides correct expectations.

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