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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: results should be cached rather than re-read, install returns an archive with exact hashes, and installation bytes must not be transcribed. However, cryptic constraints like 'bounded display' are unexplained, and leftover phrasing ('never transcribe installation bytes') lacks context an agent can act on.

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?

Efficient in length but densely packed with nested clauses and jargon; the opening parenthetical and 'bounded display' phrasing cost comprehension. The default-value and approval guidance is front-loaded reasonably well, but clarity suffers from cramming five distinct ideas into three sentences.

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, no-required-argument read tool with full schema coverage and annotations, the description covers scope, defaults, caching, and the special install view. It leaves somewhat ambiguous what the returned content looks like and what 'bounded display' permits, but no critical calling information is missing.

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 the schema already documents both the default SKILL.md path and the install/read distinction. The description mostly restates this, adding only the notion that valid file paths come from the manifest. 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?

Names a specific verb and resource (read the Penny operating SKILL.md plus reference files) and distinguishes it from user-saved skills via 'Product guidance, separate from user-saved skills', implicitly contrasting with penny_read/penny_edit. The parenthetical 'the SKILL.md penny_read target:skills name:Penny returns' is convoluted and slows identification, but the substance needed to pick this tool is present.

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 concrete conditions: default to SKILL.md, fetch manifest references only when their cues apply, and reuse files already read in this conversation. It also flags that view:install should come after user approval. It stops short of stating a hard when-not or naming the alternative tool for user-saved skills.

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