get_zpa_scim_attribute

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

The readOnlyHint annotation already communicates safety; the description's '(read-only)' is consistent and adds a small amount of clarity. The genuine value-add is disclosing the dual list-vs-fetch-by-ID behavioral modes, which the annotation doesn't convey. However, it omits details about pagination behavior, response format, or the substantial query-filtering foot-guns (which live in the schema, not the tool description). No contradiction — the description and annotation agree.

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?

One clean sentence front-loaded with the primary verb 'List', followed immediately by the secondary mode. Every word earns its place — zero fluff, no redundant phrasing. The parenthetical '(read-only)' is the only add-on and it's informative. Exemplary economy.

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 6-parameter tool with no output schema, the description covers the basic operational modes but leaves real gaps. It doesn't address pagination parameters, the search parameter's semantics, or anything about the return value shape — especially important since no output schema exists. The critical snake_case-vs-camelCase warning is buried in the schema, not surfaced here. The query param's schema description helps, but the tool-level description does the minimum.

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?

With schema description coverage at only 17%, the description must compensate — and it partially does. It ties 'named IdP' to idp_name (the sole required param) and 'fetch one by ID' to attribute_id. But page, page_size, and search receive zero semantic context in the description, and the query param (despite its excellent schema-level documentation) is unaddressed. Adequate for the two most important parameters, thin on the rest.

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?

Clear imperative verbs 'List' and 'fetch' with a specific resource 'ZPA SCIM attributes' and scope 'for a named IdP'. It distinguishes from the very similar sibling get_zpa_saml_attribute by the 'SCIM' resource qualifier and implies attribute vs. group semantics vs. get_zpa_scim_group. Loses a point for not naming sibling alternatives explicitly, but is much stronger than the typical getter.

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 dual-mode phrasing ('List... for a named IdP, or fetch one by ID') implies when to use which mode but never states explicit when-to-use vs. alternatives ('if you need SAML attributes, use...'). The '(read-only)' note and the IdP-scoping are useful context. Guidance is implied, not explicit — no exclusions or named alternatives.

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