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

Beyond the readOnly/non-destructive annotations it discloses real behaviour: no block configuration is included, the index is limited to requested sections, and definitions are returned separately. However, 'nativeRefsOmitted=true exige sectionRefs ou query/fields' references parameters (nativeRefsOmitted, query, fields) that do not exist on this tool and are not flagged as belonging to a sibling, which risks misleading a caller into passing rejected arguments given additionalProperties=false.

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?

The most important constraints (lightweight structure, ref reuse, load-once-then-apply) are front-loaded, but the prose is a dense semicolon-chained block of jargon that mixes this tool's semantics with another tool's parameters, so several sentences cost more parsing effort than they return.

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?

Annotations cover the safety profile and there is no output schema, so the description reasonably takes on describing return shape (componentRefs, sourceHeaderRefs, nativeRefsOmitted). It remains incomplete for a 5-parameter call: snapshot is undefined, and references to query/fields point outside the schema without clarification.

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 0%, so the description must carry parameter meaning. It does explain source ('draft par défaut ; published pour une correction en direct'), index ('Index limité aux sections demandées') and implies sectionRefs scoping, but 'snapshot' is only named and never explained (its 24-char identity/consistency role is left opaque) and pageId is unaddressed.

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?

The opening 'Structure légère complète : relations par références courtes, sections et snapshot' plus the later detail on componentRefs and sourceHeaderRefs makes clear this returns a lightweight structural index of a page rather than full block configuration. The one weakness is that no explicit verb is used and nothing distinguishes it from close siblings like get_page_outline or get_page_blocks; only get_page_elements is named.

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?

Strong workflow routing: 'Réutiliser ces refs via get_page_elements avec fields ciblés avant de reconstruire un composant' and 'Charger une fois, puis envoyer les modifications ensemble avec apply_page_changes' give concrete when-and-with-what guidance, and 'source draft par défaut ; published pour une correction en direct' tells the agent when to switch source. It stops short of explicit exclusions against the structurally similar siblings (get_page_outline, get_page_blocks).

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