mesh_inspect

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description still adds real value beyond them: bounded paging, the stale-revision failure mode ('fail instead of mixing different meshes'), the 1..1000 limit range, and the dimension=-1 sentinel.

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 terse sentences, each carrying distinct information, with the core read scope front-loaded and constraints (revision, limits, dimension) packed into single clauses. No filler.

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 shape need not be explained, and the description covers scope, paging discipline, and revision consistency. It is close to complete for a read/pagination tool, with only the offset and session parameters left to the schema's bare titles.

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 compensate. It defines the limit bounds and dimension=-1, but never explains expected_revision's type/source, session_id, or the node_offset/element_offset paging semantics beyond the generic word 'pages'.

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: reading bounded node/connectivity pages and counts from a mesh. 'completed mesh' scopes it relative to mesh_generate/mesh_configure, though it never names a sibling to route between mesh_inspect, mesh_quality, and geometry_inspect.

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?

'from the completed mesh' implies the prerequisite that a mesh must already exist. The instruction to retain expected_revision across pages is genuine usage guidance for pagination, but there is no explicit when-to-use/when-not or alternative-tool routing.

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