find_links

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds meaningful caveats beyond that: 'Links are parsed from card text, not verified rulings', the instruction to read evidence/ruling_flags and validate_deck, the Genesys point-limitation rule, and more_not_shown for truncated items. These are real behavioral disclosures an agent cannot get from 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?

It is front-loaded with purpose and the 'fetch' definition, but the body is a dense, indentation-heavy enumeration of output sections with idiosyncratic spacing that reads like copied field docs rather than a curated description. Much of it is necessary given no output schema, but the structure is hard to scan.

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?

With no output schema, the description usefully enumerates and explains each result section, which is genuinely helpful. But for a 9-parameter tool at 0% schema coverage it omits how the input options (cards vs decklist vs ydk_path/ydk_text, archetypes, limit) relate, so an agent still can't call it correctly from the description alone.

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% across 9 parameters, so the description must carry the burden. It explains format, point_cap/point_cap-vs-max_points interaction, but leaves cards, decklist, ydk_path, ydk_text, archetypes and limit entirely unexplained, including the mutually-exclusive deck-input options — a significant gap.

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 opening line states the resource produced: bridges and support (cards that 'fetch' your cards) for a deck or a few cards, constrained by format and budget. The definition of 'fetch' makes the domain precise. However it never distinguishes itself from the similarly named sibling find_lines, leaving an agent to guess which retrieval tool to pick.

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?

There is partial routing guidance ('check these first' for your_archetypes_unplayed, 'validate_deck any final list', and the Genesys point-cap rule), but no explicit statement of when to use find_links versus find_lines, search_cards, or archetype. Usage is implied by the output-section list rather than declared.

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