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

With no annotations, the description carries the burden and does real work: it discloses eventual consistency ('Refreshes after append/create within 30s') and the fact that a post-write call returns stale: true rather than blocking. It could also mention error cases like undeclared tables, but the disclosed behavior is substantive.

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 sentences pack the core return contract and a useful staleness behavior with no filler. The main output list is front-loaded before the timing caveat.

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?

For a tool with no output schema, the description lists most return fields (column type/statistics/role; table row count/keys/suggestions) plus stale behavior. It stops short of covering error handling for unknown/undeclared tables, but it is otherwise sufficient for an agent to call it correctly.

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 both parameters are already documented and baseline is 3. The description adds no parameter-specific details beyond calling the target a 'declared table.'

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 verb 'Return' plus 'generated semantic model for a declared table' names the operation and includes a detailed inventory of output. It does not explicitly differentiate from host.table.schema or host.table.models, though the semantic-model focus makes it distinguishable.

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?

The description implies this tool is for inspecting the generated semantic model and notes staleness behavior after append/create, which gives timing context. It never states when to choose this over siblings like host.table.schema, host.table.models, or host.table.query, and offers no exclusions.

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