graph_discover_capabilities

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

Beyond the readOnlyHint/idempotentHint/openWorldHint annotations, the description discloses the critical behavioral trait: it returns routing suggestions 'SEM executar nada' (without executing anything), confirming its safety as a pre-query discovery step. It also names possible sources (microsoft_graph, azure_resource_graph, azure_management, azure_authorization) and the routing output fields, none of which the annotations convey. No contradiction with annotations.

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 description is compact and front-loaded: the purpose line and the 'use before querying' rule come first, followed by dash-separated mode rules and a concise source list. The mixed Portuguese/English phrasing and slight restatement of the tool's name in the opening line are minor inefficiencies, but nothing is long-winded.

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 and 0% schema coverage, the description covers the two main modes, the routing output fields, and the supported sources, but it omits 'include_gaps' entirely and gives no example or return-format detail. Since this tool is explicitly positioned as the first-stop router ('use before consulting'), those omissions are meaningful gaps.

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 0%, so the description must compensate. It functionally explains three of the four parameters ('question' triggers routing; 'domain'/'source' trigger catalog listing), but 'include_gaps' is never mentioned, leaving its meaning and interaction with the other modes undefined.

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 states a specific purpose — capability discovery for identity — and defines two concrete modes: with 'question' it returns suggested routing (domain, capability, source, required permissions), and with 'domain'/'source' it lists cataloged capabilities. This clearly differentiates it from the many query/execution siblings in the toolset such as graph_query, graph_list, and graph_get, which run actual requests.

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 explicitly provides a trigger condition: 'Use ANTES de consultar quando não souber qual domínio/endpoint atende a pergunta' (use before querying when you don't know which domain/endpoint answers the question). Mode selection is also explicit via if/then rules, though no sibling tool is named as the alternative and no when-not-to-use exclusion is stated.

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