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

With annotations indicating destructiveHint=true, the description goes beyond by disclosing critical behavioral traits: Atisbo only READS a connected system, never writes; create returns an endpoint + signing secret shown EXACTLY ONCE and must be relayed immediately; config is stored encrypted and never readable again. These are exactly the kind of non-obvious behaviors an agent needs to know.

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 dense and front-loaded with the primary purpose (CONNECTS), and each sentence earns its place: modes summary, list-first rule, boundary expansion, read-only rule, and one-time secret warning. It loses one point because the heavy use of ALL-CAPS and the density of information could be slightly overwhelming, but nothing is redundant.

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 an 18-parameter tool with no output schema and nested objects, the description supplies the missing contexts: when to call list, catalog fallback behavior, read-only guarantee, one-time secret handling, pull-vs-instant distinction, and mode-to-parameter mapping. There is no output schema, so the return-value guidance ('catalog (ingestible sources; query filters)', 'create returns the endpoint') is appropriately brief but sufficient.

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?

Although schema coverage is 100%, the description adds crucial cross-parameter semantics: which parameters apply to which modes, that kwargs must pair with native_providers, that json_paths.raw_text is REQUIRED, and that sync_every applies only to PULL sources. It also explains consequences of parameter choices (e.g., email provisions an ingest address). This goes beyond the schema.

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 names a specific verb (CONNECTS) and resource (Atisbo sources/signals), and immediately distinguishes itself from merely describing them. It enumerates concrete modes list, catalog, create, configure, pause, resume, sync_now, composio variants, making the tool's scope unmistakable and differentiating it from siblings like atisbo_analyze or atisbo_capture.

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 gives explicit when-to-use instructions: 'Call list before any mutation', and warns against answering from an empty search, directing the agent to call catalog and read fallback. It also explains the CAPABILITIES boundary ('almost anything connects') and provides alternatives by mode. This is strong routing guidance.

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