diana_read_out

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

The readOnlyHint=true and openWorldHint=false annotations already establish the safe-read profile, and the description usefully confirms it can be pointed at a live, still-running job, which implies possibly partial results. It adds nothing about behavior on a missing or malformed file, output size limits, or how the tail interacts with the summary, and much of what it summarizes is likely already covered by the output schema.

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?

The purpose sentence is front-loaded and dense with useful specifics, followed by a compact Args block for the two parameters. No filler, though the args list duplicates a little of what the first sentence already implies about the file being read.

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 simple two-parameter read tool with an output schema present, the definition covers purpose, input meaning, and the important running-vs-finished nuance, which is enough for correct invocation. Minor gaps around failure behavior on bad paths and output volume keep it below full marks.

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?

With 0% schema description coverage, the description carries the full burden and largely meets it: path is specified as an absolute path to the .out file, and tail_lines is given meaning as the count of trailing lines with "0 for none", which is exactly the edge case an agent could get wrong. It omits the default value of 20 and any upper bound, so it is good rather than complete.

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?

Opens with a specific verb and resource ("Summarize a DIANA solver log (.out)") and enumerates exactly what the summary contains: analysis commands, load steps with convergence, errors, warnings, and termination status. It doesn't distinguish itself from log-adjacent siblings such as diana_read_tb, diana_command_log, or diana_experience_mine_logs, so an agent comparing them must infer the split.

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?

"Works on finished and on still-running jobs" gives a real usage condition, including the non-obvious case of inspecting incomplete runs. However there are no explicit exclusions or alternative tools named (e.g., when to pick this over diana_job_status for job state or diana_read_tb for tabular output), leaving the agent to infer routing.

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