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

Annotations declare readOnlyHint=true and destructiveHint=false, yet the description says the tool 'sets or clears' state that 'carries over between the user's requests on a connection.' Setting or clearing persistent state is a mutation, so an agent trusting the read-only annotation could call action=set or clear expecting no side effects. Side-effect semantics that matter this much are stated in contradiction to the structured safety metadata.

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, front-loaded with what the tool does, followed by the usage triggers; there is no filler. The first sentence is long because it enumerates dimensions, but each clause carries information.

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 7-parameter, zero-required tool with a nested object, the description explains persistence scope and the downstream consumer (export_data_slice) well. The remaining gap is that 'show' presumably returns the current POV and no output schema exists, so an agent does not know the shape of that response.

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 (pov, year, entity, planType, scenario, connection, action) is already documented, including the empty-string removal trick and the connection default. The description only adds the semantic frame that these members are reused by export_data_slice when a request omits them; it adds no format or syntax beyond the schema, 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?

The description names concrete verbs (shows, sets, clears) and a specific resource (the connection-scoped point of view: scenario, year, entity, cube, other dimension members). It also distinguishes the tool from the sibling that consumes its state (export_data_slice), so an agent can tell what it does and what it feeds.

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?

It gives concrete triggers: the user asks to keep looking at the same entity/year, to switch context for upcoming questions, or to start over. That covers show/set/clear selection implicitly. It stops short of an explicit 'do not use this when…' clause or naming a true alternative tool, so it is clear context rather than a full when/when-not/alternatives contract.

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