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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, yet the description still adds matters the agent could not infer: OAuth account:read consent is required, the tool is unmetered, discovery cannot grant access, authority is rechecked per page, and provider failures surface as explicit errors. Some space is spent restating the non-destructive guarantee in a generic list of untouched resource types, which is boilerplate against the annotation.

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 paging and auth facts are reasonably front-loaded, but several sentences are filler, notably 'Use supercatch_get_capabilities for this read in the connected account' and 'Supply only the fields in its strict input schema', which convey nothing. The long enumeration of untouched resource categories ('No prices, inventory, orders, automation...') pads the middle.

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 read-only paginated discovery tool with a full schema and an output schema, the description covers the remaining burdens: consent scope, paging termination, cursor expiry, per-page authority recheck, and error behavior. The one missing piece is how this catalog differs from the other catalog/help siblings in the same server.

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 limit and cursor semantics are already fully documented in the schema, and the description only echoes 'bounded pages'. It does add one piece of meaning beyond the schema, that expired cursors require a fresh search, but this is largely restated by the cursor field's 'Restart after any change' note.

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 ('Discover installed MCP capabilities') plus the paging scope, which is far more informative than the title alone. It does not, however, differentiate itself from plausible siblings such as supercatch_get_api_catalog or supercatch_get_help_resource, so an agent must guess which catalog tool to call.

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?

Gives real invocation guidance for pagination ('Follow next_cursor until has_more is false') and recovery guidance ('Expired cursors require a fresh search'), which is useful. But the only selection guidance is the circular 'Use supercatch_get_capabilities for this read in the connected account', and no alternative or when-not-to-use is named.

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