architect_runs_observe

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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower; the description still adds value by stating the tool is purely passive ('starts no work') and naming the data it observes, which matters in a family containing runtime_tick and runs_start. It does not cover pagination/cursor behavior or any limits on the event stream.

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?

A single compact sentence with the two data sources front-loaded and the non-effect clause trailing. Nothing wasted.

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?

There is no output schema, so the description should carry more of the return-shape and cursor burden, and it only hints at 'events and task snapshots'. For a 3-parameter observation tool with undocumented cursor semantics, it is adequate but leaves real gaps.

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 coverage is only 33% — 'workspace' is documented, but 'after' and 'database_id' are bare. The description never explains that 'after' is likely a cursor for incremental event reads, nor what 'database_id' selects, so it fails to compensate for the coverage 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 ('Read') and two concrete resources ('durable core events and task snapshots'), which is far more informative than the tool name alone. The clause 'starts no work' implicitly separates it from architect_runs_start and architect_runs_control, though it never names those siblings directly.

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?

'Starts no work' signals that this is the passive counterpart to the runs_start/control tools, so usage is implied rather than stated. It gives no explicit condition for choosing this over architect_runtime_status or architect_sdd_read, both of which plausibly overlap as read paths.

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