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

Read-only, idempotent, non-destructive, closed-world are already declared by annotations, so the bar is lower. The description goes beyond them by disclosing ordering (Building Check Framework, Substructure to Environmental), pagination semantics (nextCursor) and the shape of returned data, including side payloads like framework sections and the severity scale that an agent would not otherwise anticipate.

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?

A single dense sentence that is front-loaded with the verb and resource, then layers ordering, pagination, filters and return fields. Packed but orderly; slightly list-heavy, and the long clause chain takes effort to parse, but no sentence is wasted.

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, yet the description usefully summarizes the fields (title, section, short answer, canonical URL) plus the framework sections and severity scale, and explains pagination via nextCursor. For a 4-parameter read tool with annotations, what remains missing is explicit routing to the sibling get_technical_page and the meaning of limit.

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 75%: limit has no description at all (only default 15 and max 50), while cursor, section and page_type are documented in the schema. The description adds the concept of one section or page type filtering and mentions nextCursor, but adds no new syntax, matching behavior, or default/cap detail for limit beyond the schema.

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 (list the Moyne Ross Technical Library pages) and explains what the collection contains: one page per building element and functional space, ordered by the Building Check Framework. It distinguishes itself implicitly from get_technical_page (singular fetch) but never names that sibling or explains the split.

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?

Usage is implied by the description ('a page at a time', 'optionally for one section or page type'), which suggests browsing and narrowing. There is no explicit when-to-use/when-not guidance and no reference to get_technical_page or list_papers as alternatives, so an agent must infer that this is the enumeration tool and get_technical_page the single-page tool.

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