graph_as_of

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine behavioral context: reconstruction from recorded history without re-extraction, plus what is included (parent episode, labels, cardinality-one contradictions recorded at that episode). It omits pagination/limit behavior and any error semantics.

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 sentences, front-loaded with the primary query mode and no filler. The prose is extremely dense and requires re-reading, but every clause carries information rather than padding.

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 10-parameter tool with no output schema and no per-property schema text, the description covers the core selectors and the returned content reasonably well. However, canonical, limit, and repo semantics are absent, and with no output schema the agent must still guess at result shape and pagination.

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 carry all parameter meaning, and it does explain most: as_of (episode id, commit sha label, latest/working), valid_at/known_at/branch, node (exact id), query (id substring), and relations. It leaves repo, limit, and canonical completely unexplained, which is the main gap.

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?

States a specific verb ('Query') and two concrete resources: the temporal record (valid_at/known_at/branch) and the repository's typed code graph at an episode selector. It is dense but the agent can tell it is an as-of/time-travel read distinct from a live graph query, though it never names a sibling (e.g. query_graph) for contrast.

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 presents the two query modes and the narrowing parameters, implying when each mode applies, but gives no explicit when-to-use versus when-not-to-use, no routing to query_graph or graph_episodes, and no prerequisites. Usage must be inferred from the mode descriptions.

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