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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, yet the description adds substantial behavior: which content is deliberately excluded (staff notes, internal comments, contact/session data, attachments, images), the authorization model (OAuth scope plus live case ownership, seller/store authority insufficient), the error contract (invalid fields, unavailable stores, foreign or deleted targets fail without private records; expired cursors need a fresh search), and the Shared MCP Baseline 1.0.0 envelope. This goes well past the annotation surface and is exactly what an agent needs before calling.

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 consent requirement is stated three separate times ('under separate account:support:read consent', 'Requires OAuth account:support:read consent', 'Requires separate account:support:read consent'), and 'Use supercatch_get_support_case for this read in the connected account' adds nothing. The useful information is front-loaded, but the paragraph is roughly twice as long as it needs to be.

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 values need no explanation, and the description still summarizes the envelope (scope, provenance, unknowns, omissions, typed errors). Combined with the ownership/consent model and the error contract, an agent has enough to invoke this correctly; only the discovery path to a valid case_id is unaddressed.

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?

There is a single parameter and schema description coverage is 100%, so the schema already documents case_id fully, including the 'store membership grants no access' constraint. The description only adds the strictness note ('supply only the fields in its strict input schema') and 'exact' semantics, 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 opening sentence gives a specific verb and resource ('Read one exact support case') plus a scope qualifier (authored by the authenticated account), which separates it from list_support_cases and list_support_case_comments. It never names a sibling explicitly, and the later sentence 'Use supercatch_get_support_case for this read' merely restates the tool name rather than differentiating it.

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?

Usage context is implied: it requires live case ownership in the authenticated account and a specific consent scope. But it never tells the agent how to obtain a case_id (e.g. 'first call supercatch_list_support_cases'), and the only explicit exclusion is that store membership does not grant access. Guidance exists but requires inference.

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