Bloom get history

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Read-only' largely restates structured data. The description does add genuine context beyond annotations: the on-disk location of the data and the JSON return shape, but it says nothing about what happens when the file is absent or how large the history can grow.

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?

Four short sentences, front-loaded with the core action and the file location, with no filler. 'Read-only' is a minor redundancy against the annotations and just barely earns its place as reassurance, keeping this from a 5.

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 two-optional-param read tool with full schema coverage, rich annotations and an output schema (so return values needn't be spelled out), the description covers what it is, where the data lives and which sibling writes. Only the empty/missing-file behavior is left implicit.

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% and both optional filters (model, behavior) are already documented in the schema with their own descriptions. The tool description adds no filtering semantics of its own—no mention of how filters combine or what an unfiltered call returns—so the baseline 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 ('Read persisted Bloom evaluation rows') and even names the backing store, so the agent knows exactly what data comes back. It explicitly distinguishes itself from the write path by naming bloom_evaluate_model as the way to add rows.

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?

The sentence 'Use bloom_evaluate_model to add rows' cleanly routes the agent between the read sibling and the write sibling. It gives clear context for when to use this tool but offers no exclusions about the other history-adjacent tools (e.g. get_calibration_history), so it falls short of a full when/when-not treatment.

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