sas_sources

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

readOnlyHint=true already tells the agent this is a safe read. The description adds one genuinely useful behavioral fact beyond the annotations: it 'starts no session', so it is a side-effect-free probe rather than one that provisions a CAS session. It still omits what the check actually evaluates (sign-in validity vs. configuration) and what the response looks like.

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?

Two short clauses, front-loaded with the core question the tool answers, followed by the parameter note. Slightly awkward phrasing (parenthetical, inline backticks) but no wasted sentences.

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 one-parameter read-only probe with no output schema, the agent still needs to know what comes back (ready/not-ready flag, connection identity, error semantics) and how to react to a negative result. The description covers the parameter and one behavioral constraint but leaves the return contract implicit.

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 carries the full burden for the single parameter, and it does: 'connection' is documented as 'a saved SAS Viya connection' with a stated default of the active one. That meaningfully exceeds the bare anyOf string schema, though it does not clarify name vs. id format.

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 frames the tool as a readiness check ('Whether SAS Viya is set up and signed in') scoped to SAS libraries / caslibs sources, which is more than a restatement of the name. However, 'sas_sources' is an opaque name and the description never states what the check returns (a boolean, a state object, a list of sources), nor how it differs from close siblings like sas_viya_state or connection_health. The purpose is inferable but not crisp.

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?

There is no explicit guidance on when to call this versus sas_viya_state, sas_viya_test, sas_libraries, or cas_caslibs. The clause 'starts no session' hints that it is a cheap precondition probe, but the agent must infer the usage context rather than being told it.

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