graph_directory_objects

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

Annotations cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the description needn't restate safety. It adds a meaningful behavioral trait beyond annotations: it correlates the same identity across domains while preserving the source of each piece of evidence, which tells the agent the output merges identities and traces provenance. It does not mention limits, pagination, or what 'domains' values are valid beyond the single example.

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?

Three short sentences, front-loaded with the core action before the parameter detail. No filler, though the quoted description includes leading/trailing whitespace artifacts. Efficient overall.

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 zero-required-parameter, cross-domain correlation tool with no output schema and 0% schema description coverage, the description should do more. It omits how 'limit' interacts with results, how 'question' drives inference, and what the correlated output looks like. It is not misleading but is incomplete for accurate invocation.

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 and it only partially does. It clarifies the 'domains' parameter format and the empty-value fallback, which is genuinely useful, but says nothing about 'limit' (a default of 100 with no semantics) or 'question' (how it drives domain inference). Two of three parameters remain undocumented.

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 verb and resource ('Coleta objetos de diretório de um ou mais domínios') and adds a cross-domain correlation function, which is reasonably clear. However, it does not distinguish itself from the many sibling graph_* tools (graph_query, graph_list, graph_get, graph_relationship), leaving an agent unable to tell why this tool exists versus those. The purpose is legible but lacks sibling differentiation.

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 description explains the domains parameter behavior (comma-separated, inferred from the question if empty) but gives no explicit when-to-use guidance and no comparison to the numerous sibling tools that also retrieve directory objects. An agent is left to guess when this tool is the right choice over graph_query or list_users.

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