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

Annotations already declare readOnly/safe/idempotent/closed-world, so the description focuses on what annotations cannot say: the corpus size (~435 titles), the default one-page shape, and the warning that full chapter notes 'can be very long'. That size/latency warning is genuinely actionable. It stops short of describing the response envelope or what happens when a title is not in the corpus.

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?

Three sentences, front-loaded with the return payload, then trigger examples, then the opt-in caveat. Every sentence carries distinct information and the costliest decision (full_text) is deferred to the end where it reads as a caution.

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?

An output schema exists, so return values need no prose explanation, and annotations cover the safety profile. Given a 2-parameter read tool, the description supplies everything an agent needs: what comes back, when to call it, and the one flag that changes cost.

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 earns above that by converting full_text into a usage rule ('only when the user explicitly wants...') rather than merely restating the schema's 'include full chapter contents'. The title parameter is only implied, not given format or matching guidance.

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 and resource ('Return MRB's one-page summary of a book') and enumerates the payload: overview plus chapter-by-chapter notes. The ~435-title corpus bound is a concrete scope statement that lets an agent distinguish this from search_books.

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 real trigger phrasings ('summarize Atomic Habits', 'what is Sapiens about?') and an explicit condition for the optional flag ('only when the user explicitly wants the complete chapter notes'). It does not name a sibling such as search_books as the alternative when no summary exists, which keeps it short of a 5.

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