ingest_observation

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

The description discloses key behavioral traits: it may create or update entities (a write operation) when reconcile=true, it re-identifies by Euclidean proximity, boosts confidence, and optionally reconciles against the expected frustum. It also returns a specific shape {ok, matched[], created[], lost[], reconcile}. Annotations already flag readOnlyHint=false, so the description adds useful context about what actually happens (merge, re-identify, confidence boost). Doesn't mention idempotency or failure modes, hence a 4 not 5.

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?

Front-loaded with the core action, then behavioral details, then a usage-routing sentence. Efficient and well-structured, though the return shape list and the phrase 'This is the perception writer' could be trimmed without loss. Every sentence carries some value, but not maximally tight.

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 6-parameter mutation tool with no output schema, the description does a good job covering what the tool does, its write behavior, and its return shape. It explains the reconcile option's effect and routes the agent away from update_entity. Missing: what happens when no match is found (created vs lost semantics), and any mention of required permissions or failure modes. Given annotations cover safety, this is nearly 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 83%, so the schema already documents most parameters thoroughly (project, reconcile, detections with nested fields, observer_pose, visual_state_id). The description adds meaning for reconcile ('reconcile against the expected frustum') and explains the merge logic but doesn't add syntax or format beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource ('Merge vision detections into the world model') and explicitly distinguishes from the sibling update_entity ('use ingest_observation instead of update_entity when merging camera or sensor perception detections'). This is a clear purpose with sibling differentiation. However, the title is null and some phrasing like 'perception writer' is jargon-adjacent rather than precise.

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?

Provides a clear condition for choosing this tool over the sibling update_entity (merging camera/sensor detections vs manual authoring). The reconcile parameter's behavioral trigger is also stated ('optionally reconcile against the expected frustum'). However, no exclusions or prerequisites are given, and it doesn't address when to use it vs. recording outcomes or querying entities.

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