get_observations

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that source can be 'memory' or 'observation' and mentions include_suppressed indirectly through context, but it does not elaborate on return format, error handling, permissions, or whether the operation is strictly read-only. It is not contradictory, but it is minimal for an unannotated tool.

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 two sentences, front-loaded with the primary action ('Fetch complete details by IDs') and followed by concise workflow guidance. Every sentence serves a purpose, with no redundant wording or unnecessary elaboration.

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 simple fetch-by-IDs tool with rich schema descriptions, the description adequately covers the workflow and source semantics. It does not explain return values (no output schema exists), but it provides the critical context of how to use it with search and what source values are valid. The schema fills in the remaining parameter details, so the description is reasonably complete.

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 100%, so the baseline is 3, and the description adds value by specifying that the source value should come from 'search.next_step.source or each result.source'. This provides concrete, actionable guidance beyond the static schema description, particularly for the source parameter, making it easier for an agent to populate correctly.

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 opens with 'Fetch complete details by IDs', a specific verb+resource statement that clearly states the tool's function. It distinguishes itself from sibling tools like search by explicitly positioning it as a follow-up to search() and by describing the supported source types, making it clear this is a retrieval tool for full observation records rather than a search tool.

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 explicitly says 'Use after search()' and instructs to pass selected IDs and the exact source from search results, establishing a clear when-to-use workflow. While it does not name alternative tools or provide exclusions, it gives enough context for an agent to know this is intended for post-search retrieval, not for broad searching.

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