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

Beyond readOnlyHint=true, the description discloses the two-step flow, the dump-mode last-N-lines behavior, the exact return shape { logs_url, lines }, and the partial-failure case where only logs_url comes back. That failure-mode note is genuinely useful context an agent cannot get from annotations; rate limits or log retention are still unstated.

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?

Three sentences, front-loaded with purpose, then mechanism and return shape, then the failure caveat. The inline API route is slightly more detail than an agent needs, but nothing is redundant or bloated.

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, yet the description specifies the return object and the degraded return case, and the schema fully covers the two inputs. An agent has everything needed to call it and to interpret what comes back.

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 both `app` and `lines` are documented with bounds and defaults in the schema itself. The description only echoes 'last N lines' and adds no format or semantics beyond that, so the baseline of 3 applies.

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 and resource: 'Fetch recent application log lines', and explains the internal mechanism (authenticated logs_url then dump-mode download). The resource is distinct from siblings like scalingo_list_app_events or scalingo_get_app_stats, though no sibling is named explicitly.

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?

Usage is implied (recent log inspection for an app) and the fallback path is described, but there is no explicit statement of when to prefer this over scalingo_list_app_events or scalingo_request, and no exclusions or prerequisites are given.

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