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

No annotations exist, so the description carries the full burden and does so: it declares 'Read-only', discloses the ranking method (live pricing + benchmark quality, hard filters, quality-per-dollar scoring), the return shape (best match plus up to 3 alternatives), and non-obvious fallback behavior — client restriction is a filter not a boost, explicit client wins, omission triggers handshake inference, and unknown names return an unfiltered result plus a note.

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?

Purpose and alternatives are correctly front-loaded, but the paragraph is dense and includes a full enumeration of 14 recognised client names that the client parameter's schema description already lists in greater detail — roughly a fifth of the text is redundant. It is informative rather than padded, but it is longer than it needs to be.

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 16-parameter, no-annotation, no-output-schema tool, the description covers what matters most: purpose, alternatives, read-only safety, ranking method, and return shape. The remaining gap is that the cost/currency/budget parameters are left entirely to the schema, which is acceptable given 100% schema coverage but means the description alone would not tell an agent the tool supports currency conversion or budget hard-filters.

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%, so the baseline is 3; the description earns above that by explaining the semantics an agent would otherwise get wrong — that client restricts rather than boosts the candidate set, the precedence order, and that omitting it degrades to every priceable model. It does not touch the other 13 parameters (budget, currency, token averages), but the schema already documents those fully.

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?

Opens with a specific verb+resource ('Recommend the optimal LLM model') and immediately names the mechanism (classifies free-text into task_type, runs it through the same routing engine behind /router/recommend). It explicitly distinguishes itself from the two nearest siblings, predict_cost and optimize_workload, so an agent can choose without opening any schema.

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 explicit when-to-use-this vs when-to-use-alternatives routing: 'use predict_cost first if you also want per-model cost estimates for an actual prompt, and optimize_workload if you have several distinct task types to route at once.' It also states the input precondition (free-text description, no need to know the task_type vocabulary) and how to get a filtered vs unfiltered answer via client.

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