extend_from_formulas

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

Annotations already mark the tool as read-only and closed-world, and the description adds substantial behavioral detail: validation requires all but at most the first 3 terms to agree with at least 6 known terms, 'ext=True' pulls DATA plus b-file terms, conjectural lines are excluded, and new terms are returned from n = offset + n_terms. It also warns that the relation is the entry's own claim, which is valuable context beyond annotations.

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 description is front-loaded with the central question and packs useful detail, but it is a dense single paragraph with many parenthetical asides and nested clauses that make it harder to scan than necessary. Every sentence carries information, but the structure could be clearer.

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 complex, multi-step tool with no output schema, the description explains the core algorithm, validation rules, conjectural skipping, and partial return behavior. However, it leaves parameter semantics for 'anum' and 'max_new' unclear and does not fully specify the return structure beyond 'new terms from n = offset + n_terms on.'

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 0%, so the description must compensate for all three parameters. It explains the effect of 'ext' ('ext=True: DATA + b-file') but does not define 'anum' (presumably the OEIS A-number) or 'max_new' (presumably the maximum number of new terms to return), leaving two of three parameters undocumented.

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 specific action: extending an OEIS entry from its own stated relations by parsing FORMULA lines and transform phrases, validating against known terms, and returning new terms. It distinguishes itself implicitly from retrieval siblings by focusing on extension rather than lookup, though it does not name alternatives.

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?

Usage is implied: call this tool when you want to extend a sequence using the entry's own claimed relations. The description notes that conjectural lines are skipped, but it does not explicitly state when to prefer this over siblings like guess_recurrence or identify_transform, nor does it describe any preconditions.

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