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. 'Retrieve' implies a read-only operation, but there is no statement about side effects, failure behavior (e.g., missing name), permissions, or whether results can only be read. This is minimal coverage for an unannotated tool.

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 a short single sentence with no filler and the verb is front-loaded. However, it is so minimal that it leans toward under-specification rather than purposeful conciseness; it could have added a short usage note without losing brevity.

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 one-parameter retrieval tool with an output schema, the description is adequate but not thorough. It doesn't confirm read-only semantics or clarify the relationship between the input name and previously run screens, but the output schema does resolve some return-value ambiguity.

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 the name property already carries its own description ('Safe persistence name'), so the tool description adds no parameter meaning. Per the rubric, a baseline of 3 is appropriate 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?

The description uses a specific verb ('Retrieve') and a clear resource ('saved screening result'), which distinguishes it from sibling tools like run_stock_screen that would create or run a new screen. It doesn't describe what the result contains, 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?

There is no explicit guidance on when to use this tool versus siblings such as run_stock_screen. The word 'saved' implies it is for previously stored results, but the description never states a direct comparison, when not to use it, or what makes it preferable over running a new screen.

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

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

Annotations are absent, so the description must carry the full burden of disclosing behavior. It only states that the output is normalized news and recent, which gives a minimal idea of the data nature but does not mention what exactly happens (e.g., returns a list, sorting, pagination, rate limits, or whether it is strictly read-only). This is adequate only at the most basic level.

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 a single, concise sentence with no redundant words or promotional fluff. It directly achieves its purpose and is perfectly sized for the tool's simplicity. Nothing extra needs to be removed or rewritten.

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?

The tool is simple, has only two parameters fully described in the schema, and has an output schema, so the description need not explain return values. The overall context is clear enough to call the tool correctly, though adding 'from a given Yahoo Finance symbol' would make it even more self-contained. Still, given the combined context, it is largely complete.

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?

The description does not add meaning beyond the input schema, but the schema itself has 100% description coverage for both parameters ('Yahoo Finance ticker symbol' and 'Maximum news age in days'), so the baseline of 3 is appropriate. The description word 'recent' does loosely reflect days_back, but no extra detail is provided.

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 specific action ('Get') and resource ('normalized recent Yahoo Finance news'), clearly indicating a news retrieval operation. It does not explicitly differentiate itself from sibling tools like run_stock_screen or get_screening_result, but the nature of these sibling tools is clearly distinct, so the purpose 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?

There is no guidance on when to use this tool versus the sibling tools. The description does not mention typical use cases, alternatives, or any conditions that would steer the agent toward or away from this tool. The only contextual clue is the name and the schema, which is insufficient.

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

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

With no annotations provided, the description carries the disclosure burden. It does state that the watchlist is safely persisted and includes destructive delete operations, which is helpful. However, it does not explain what 'safely persisted' actually means, whether operations are reversible, or whether any authentication or permissions are required.

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 a single front-loaded sentence that directly communicates the tool's scope with no wasted words. Every part of the sentence contributes to understanding the tool, despite some slight vagueness in 'safely persisted.'

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?

The description and output schema cover basic invocation but leave important semantics unstated. In particular, it is unclear how 'update' behaves relative to 'create' and 'delete' (replace, overwrite, or mutate), what the preconditions are for each action, and what 'safely persisted' implies for cleanup or consistency.

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?

The input schema already describes two of three parameters with meaningful details (action enum and name pattern), though symbols is more generic. The description does not add further parameter-level meaning, which is acceptable at 67% schema description coverage but does not exceed the baseline.

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 clearly names the tool's purpose with specific actions (create, update, delete, retrieve) and the resource being acted on (a persisted watchlist). It also distinguishes itself from sibling tools like run_stock_screen and get_stock_news, which are not watchlist management operations.

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 description implies when to use the tool (whenever the agent needs to manage a watchlist) but does not explicitly articulate when not to use it or how it relates to the sibling tools. It provides no direct comparison or exclusion guidance, leaving the agent to infer context from the tool name and sibling set.

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

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

With no annotations provided, the description carries the full burden of disclosing side effects. The parameters watchlist and save_result suggest possible persistence or retrieval, but their purpose is not explained in the description. The tool might write results or consult a watchlist, yet the description only says 'run a screen', which is ambiguous regarding side effects and state changes.

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 a single, concise sentence with no redundant wording. It efficiently communicates the core purpose and enumerates the screen types without unnecessary detail, making it easy to parse and understand.

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?

Given the tool has 4 parameters including a nested object and an output schema, the description is far too brief. It does not explain the structure of the criteria object, the meaning of watchlist and save_result, the expected behavior for each screen_type, or what the returned data will look like. The agent cannot confidently invoke the tool correctly based on this 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 only 50% (criteria and screen_type have meaningful descriptions; watchlist and save_result only have the generic 'Safe persistence name'). The tool description does not add any clarification for these parameters, nor does it explain what 'criteria' should contain or how watchlist and save_result are used. The description fails to compensate for the missing schema detail.

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 clearly states the action ('Run') and the resource ('stock screen'), and enumerates the specific screen categories (technical, fundamental, options, news, custom). It distinguishes the tool from siblings such as manage_watchlist, get_screening_result, and get_stock_news, which handle different aspects of screening work.

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 description does not provide any guidance on when to use this tool versus the sibling tools. It does not mention that it is for executing a screen to get results, nor does it contrast with retrieve_screening_result or manage_watchlist. The phrase 'legacy' hints at a deprecated nature but is not elaborated, leaving the agent without clear selection criteria.

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