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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: matching runs against a fixed term list with no model call, the same words give the same answer, and a model with an accuracy gap is still the served model of its thing. That determinism and the fit/accuracy distinction go beyond anything in the 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 purpose is front-loaded in the first clause, but the rest is a sprawling run-on of comma-spliced clauses that pack output-format, semantics and fallback behavior into undifferentiated prose. Much of that content is necessary given the absence of an output schema, yet the presentation makes it hard to parse and should be broken into discrete statements.

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 must and does explain the return shape: a few cards and solvers, each with fit first then accuracy, including the three-word evidence vocabulary and the names that feed other tools. It also covers the no-match outcome. What is missing is a crisp statement of input expectations (how short or literal the description should be).

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 both parameters are documented there, including limit's default of 3. The description only reinforces 'in plain words' for description and adds an example query, offering no syntax or constraint detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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: it finds the served model matching a plain-language description of a real thing. It distinguishes itself from siblings by naming list_cards, list_solvers, describe_card and describe_solver as the tools that share its vocabulary and take its returned names. The domain jargon ('served model', 'cards and solvers') is idiosyncratic but the core action is unambiguous.

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 effectively routes the agent: find_model locates and names the model, while describe_card or describe_solver 'gives the range and every refusal', implying the lookup-then-detail flow. It also covers the no-match path and says where requests go when nothing served fits. It never states an explicit trigger for the inverse case (when to skip find_model and go straight to describe_card), so it falls short of a full when/when-not statement.

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