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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by disclosing the return shape (title, project, status, rating) and that pagination applies. It stops short of saying what happens on an out-of-range page or how results are ordered, which is the only remaining gap.

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 compact sentences, each load-bearing: the first defines scope and exclusions, the second routes to alternatives and lists the narrowing options. The return-shape caveat is front-loaded before the alternatives, which is the right order for a browsing 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?

With no output schema, the description carries the burden and does it well by naming the four summary fields and confirming the writing body is excluded, while annotations cover the safety profile. Ordering and empty-result behavior are the only omissions, which is minor for a simple paged list.

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 description coverage is 100%, so every parameter's meaning is already documented with defaults and ranges. The description's 'narrowed to one project, and searched by title' restates the schema rather than adding syntax or matching-behavior detail, so baseline 3 applies.

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 plus the scope ('the scripts the signed-in user can reach') and explicitly names what it does NOT return ('never the writing itself'). It distinguishes itself from get-script and search by name, so an agent can separate the three without opening any 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?

Gives explicit routing: use get-script for the sections of one script, use search when hunting a phrase rather than browsing, use this when browsing. It also states the two narrowing modes (one project, title search), leaving no ambiguity about which sibling to pick.

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