submit_feed

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the error condition via the Raises section (BingWebmasterError if feed cannot be submitted), which is useful. However, it omits side effects (e.g., whether submitting an existing feed replaces it), idempotency, rate limits, or auth requirements. The Raises note adds some value but the mutation's side-effect profile is unaddressed.

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 compact and well-structured: a one-sentence purpose up front, followed by an Args block and a Raises block. The front-loaded purpose sentence makes the tool's role immediately clear, and each section (args, error) earns its place. Some brevity comes at the cost of missing guidance, but structurally it is efficient and well-ordered.

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?

This is a mutation-style tool with no annotations, 0% schema coverage, and an output schema present but not described. For an agent to invoke it correctly it would benefit from knowing side effects, idempotency, prerequisites (site ownership/verification), and whether re-submission overwrites an existing feed. None of this is covered. The two parameters are documented at a basic level, but the broader behavioral context is missing, making this incomplete for a mutation tool with zero annotation support.

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. The Args section adds basic meaning beyond the bare schema: site_url is 'The URL of the site' and feed_url is 'The URL of the sitemap feed.' This is minimal but genuinely clarifies the role of each parameter versus the schema alone. It doesn't specify URL formats, whether site_url must be a verified/owned site, or feed format constraints, so it's adequate but not rich.

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 clear action: 'Submit a sitemap feed for indexing' — a specific verb (submit) plus resource (sitemap feed) plus purpose (for indexing). This distinguishes it from sibling retrieval tools (get_feeds, get_feed_details) and deletion tools (remove_feed), and the resource type separates it from submit_url and submit_content. It doesn't explicitly name any sibling, but the action+resource is specific enough to differentiate.

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 no guidance on when to use this tool versus alternatives. Among siblings there are several submission tools (submit_url, submit_url_batch, submit_content) and feed-management tools (get_feeds, remove_feed) that an agent could confuse it with, but the description offers no selection criteria, prerequisites (e.g., site must be verified/owned), or conditions that would make this the right choice.

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