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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: it discloses that the log tail is bounded and drawn from the most recent start attempt, and that on a crash-looping container the tail reveals the crashed attempt's output (often naming required env vars). It stops short of stating truncation behavior when the container never started or whether it hits the API/agent path, so it is strong but not exhaustive.

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 purpose, then the usage trigger, then the alternative, then identification. Each sentence earns its place, though the opening sentence is dense with a parenthetical field list and runs long, which slightly slows scanning.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the record fields and describing the log tail. Four parameters, one required, all documented, and the diagnostic workflow (identify → diagnose → then change configuration) is fully specified.

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 100%, so the baseline is 3, but the description adds real meaning: it explains that the demo can be identified by either workspace_id or namespace (mutually optional), which the schema states only per-field, and frames tail_lines as a bounded tail of the most recent start attempt, adding diagnostic intent the schema does not convey.

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 resource (one Application demo's tracked record) and enumerates exactly what is returned: status, kind, branch/pr_number, image tag, container port, last_error, preview URL, expiry, plus a bounded log tail. It explicitly distinguishes itself from inspect_demo, so an agent can tell the two apart without opening either schema.

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?

Gives an explicit trigger ('crash-looping or failed demo ... before changing its configuration'), an explicit counter-case with the alternative tool ('preview does not load / does not resolve / certificate error' → inspect_demo, with the reason: it reads live namespace inventory and probes the URL), and how to resolve the identifier via list_application_demos. Full when/when-not/alternatives coverage.

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