Fire results summary

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the redundant 'Read-only' adds nothing. What does add value is the disclosure of data provenance — result files plus 'the engine log of this session' — and that it works on both finished and still-running simulations, which tells the agent the scope and freshness of the returned data.

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?

Effectively one front-loaded sentence that leads with the verb and object, then lists outputs — no wasted preamble. The trailing '[bulc-mcp rules] ...' footer is a clipped metadata injection that interrupts the flow rather than earning its place in the description prose.

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 carries the full burden of describing return contents — and it does so exhaustively, covering scalar metrics, per-device columns, activation times and available output files. For a two-parameter, read-only summarizer this leaves nothing an agent would need unexplained.

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%, with fdsPath and maxDevices both documented in the schema, so the baseline is 3. The description mentions 'every device column' (loosely implying the maxDevices cap) but adds no syntax, path-format or default guidance beyond what the schema already provides.

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?

The description states a precise verb (summarise) plus the exact resource (result files of a fire simulation) and then enumerates the concrete quantities returned — peak HRR and its time, total heat released, radiative fraction, simulated time vs T_END, per-device maxima, setpoint crossings, sprinkler/detector activation. This level of specificity clearly separates it from neighbours such as get_simulation_metrics, fire_timeseries, spr_get_results and results_detect.

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?

It implies the context ('a finished (or running) fire simulation') and appends a rule reference pointing to bulc_knowledge_search, but it never states explicitly when to reach for this tool versus get_simulation_metrics, fire_timeseries, or spr_get_results. Usage must be inferred from the content list.

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