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

With no annotations, the description carries the burden, and it does useful work: 'Read' establishes a non-mutating operation and the exclusions (no attachments, no private journals) set caller expectations about partial results. It does not address permissions or error behavior for an invalid or non-published workId, which a read tool with zero annotation coverage would benefit from.

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 sentences, zero waste, purpose stated first and the negative scope second. Nothing repeats the name or title.

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 one-parameter read tool with no output schema, the description covers what it returns (full text), the key's provenance, and what is omitted. Missing only failure-mode context for unpublished or invalid IDs.

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 single parameter is undocumented in structured fields; the description compensates by stating that workId comes from library_list, which is the key semantic an agent needs. It does not describe ID format or length bounds, but the source pointer is the material fact.

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?

Specific verb ('Read the full text'), specific resource ('published Library work'), and an explicit reference to the sibling library_list as the source of the key. An agent can distinguish it from library_list and library_tip without opening a schema.

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?

Naming workId 'from library_list' implies the correct call order (list first, then read), and the sentence 'Does not return file attachments or private journals' rules out a class of expected content. It stops short of naming alternatives for private journals or stating explicit exclusions against siblings like library_tip.

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