compute_sn_chi2

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

With no annotations, the description carries the full burden. It does disclose meaningful method details (offset-marginalised absolute magnitude, full covariance, 'fast'), which an agent needs to interpret the number correctly, but says nothing about failure modes, whether the dataset must be fetched beforehand, or any permission/cost constraints.

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 what the tool returns, followed by a compact usage sentence with concrete examples. 'Fast' is slightly informal but earns its place as a selection cue; nothing is redundant.

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?

Output schema and full parameter documentation mean the description need not cover return values or argument semantics. What is missing is workflow context — whether the SN sample must be fetched with fetch_sn_sample first, and how the calibrators option interacts with the non-Pantheon+ datasets.

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 all seven parameters are documented with defaults, bounds and enums, so the schema does the work. The description only indirectly maps the model parameters via examples (Om=0.315, w0waCDM implies w0/wa) and adds no bounds or syntax beyond the schema.

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 computation (offset-marginalised chi2 with full covariance) for one cosmology against a sample, and explicitly scopes it to a single model, which separates it from fit_sn_cosmology and compute_distance_modulus. 'Delta-chi2 between two models without a full fit' further pins down exactly what it produces.

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?

Gives concrete use cases — testing a named model such as Planck LCDM Om=0.315 or DESI DR2 w0waCDM, and computing model-to-model Delta-chi2 — which implies the alternative (a full fit) without stating it as an exclusion. No mention of prerequisites such as whether the sample must be loaded first.

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