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

Annotations only declare readOnlyHint=true/destructiveHint=false; the description adds substantial context beyond that: the run stores the last 60,000 chars of each stream and this returns the last 50,000, so t​​he tail (where tracebacks live) is kept, truncated=true plus a note when the head was cut, and the permission model (any project member, viewers included).

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 return contract, then truncation semantics, then id sourcing and exclusions, then permissions — a logical order with little waste. Slightly long at five sentences, and the 60,000/50,000 detail, while useful, is the densest part.

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?

No output schema exists, so the description must describe the return value and it does: stdout, stderr, truncated flag, and an explanatory note. Combined with the empty-result case and permission model, an agent has everything needed to call it and interpret the result.

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 100%, and each parameter already names its source tool, so the schema carries the load and baseline 3 applies. The description's only additional semantics is that a runId from another Python project yields no output, which is a modest increment.

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 (read a finished Python run's printed output) and enumerates exactly what comes back: stdout, stderr and truncated. It is clearly separable from fastero_list_python_runs (status/error without the log) and fastero_read_python_file (files the run saved).

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?

Explicitly routes the agent: get runId from fastero_list_python_runs, use that tool instead if only status/error is needed, use fastero_read_python_file for saved files. It also names the when-not case — a queued/running run or a runId from another Python project returns 'This run has no saved output'.

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