update_deep_link

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

No annotations are present, so the description carries the full burden of behavioral disclosure, and it does provide two concrete facts: the tool is deprecated and it raises BingWebmasterError on failure. However, it does not describe success behavior, side effects, reversibility, or what changing the weight actually affects. The deprecation and error clauses justify a 3, but the mutation's consequences remain largely unspecified.

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 docstring is compact and well-ordered: a one-line summary with the deprecation note front-loaded, followed by a terse argument list and an error clause. There is no redundant prose or preamble. It loses a point because several parameter lines are filler that merely restate the parameter names rather than adding meaning.

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 deprecated four-parameter tool with no annotations and 0% schema coverage, key facts are missing: the semantics of the weight enum, a pointer to the replacement tool, and any guidance on when it is still appropriate to call it despite deprecation. The output schema covers return shape, so that absence is not penalized, but the deprecation and enum gaps leave the description materially incomplete.

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, but three of the four parameter lines are nearly circular ('algo_url: The algo URL', 'deep_link: The deep link URL'). Most critically, the weight parameter's enum values (0-3) are never explained, so an agent cannot know whether higher or lower weights are heavier or what semantic each value carries. This fails to compensate for the schema's complete lack of parameter documentation.

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 'Update deep link weight' names a specific verb, resource, and attribute, so an agent knows exactly what operation is performed. The '(Deprecated)' marker adds useful lifecycle context, and the tool is distinguishable from siblings like get_deep_link or remove_deep_link_block because none of them target the weight attribute. It stops short of 5 because it doesn't explicitly contrast itself with any sibling.

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?

The only usage signal is '(Deprecated)', which implicitly tells the agent this tool is not the recommended path, but no alternative or when-to-use condition is provided. With roughly 60 sibling tools, an agent cannot determine what to call instead without external investigation. The deprecation marker is implied usage guidance at best, so it earns a 3 rather than 2.

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