BasePic

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

Annotations already declare destructive=true, idempotent=true, and readOnly=false, so the safety profile is covered structurally. The description adds genuine value beyond them by disclosing the consequence ("Its links stop working") and the credential dependency on delete_key, which the annotations do not convey.

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?

Three short sentences, front-loaded with the action, followed by the prerequisite and the consequence. Every sentence carries load and none is redundant with the schema or annotations.

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 two-parameter, no-output-schema tool whose annotations already cover safety semantics, the description supplies the prerequisite source and the visible effect of deletion. Nothing an agent needs to invoke it correctly is missing.

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 only 50%: `id` is documented but `delete_key` has no schema description. The description compensates by explaining where delete_key comes from (returned at upload or by edit_image), turning an opaque required string into a meaningful prerequisite.

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 ("Delete an image from BasePic") with a clear scope. It is trivially distinguishable from the siblings edit_image, get_image, and upload_image by its destructive action. No agent would confuse this with a read or edit operation.

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 the tool applies (you have an image to remove) and states the key prerequisite: a delete_key from upload_image or edit_image is required. However, it names no explicit alternatives and gives no when-not guidance, so usage is largely inferred from the required parameters.

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 already declare non-read-only, non-destructive, non-idempotent, and the description adds the key behavioral fact that a new asset is produced and the source is untouched — exactly the reassurance needed given readOnlyHint=false. It also discloses operation ordering ('applied in order') and the max_kb meaning (1 KB = 1,000 bytes). It does not cover auth, rate limits, or failure behavior, so not a 5.

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 operation list is front-loaded and the two sentences carry no filler; the second sentence delivers the crucial new-image semantics. The long em-dash enumeration is dense but each term maps to a real enum value, so it earns most of its length.

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 usefully names the returned fields (page_url, image_url, download_url) so the agent knows what it gets back. Given 7 parameters and 57% coverage, a few inputs (quality, filename, return_preview) remain undocumented, but the core editing contract is 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?

At 57% schema coverage the description adds real value: it clarifies the operations pipeline is order-sensitive and groups the enum values by category (rotate/flip/crop/resize vs. color and filter ops), plus explains max_kb as an output size ceiling tied to format. It leaves quality, filename, and return_preview unaddressed, and much of the op vocabulary is already in the enum/schema.

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 (edit) and resource (an uploaded image) and enumerates the concrete transform set, so the agent knows exactly what capability this is. It also distinguishes itself from siblings by stating it creates a NEW image and leaves the original unchanged, contrasting with delete_image/get_image/upload_image.

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?

'Edit an uploaded image' plus the id parameter description establishes the prerequisite (an id from upload_image or edit_image), which is clear context for when to call this. It stops short of explicit exclusions or naming sibling alternatives for non-edit scenarios (e.g., use get_image to just inspect), so it is context-clear but not fully routing.

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 already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value by enumerating the returned details, but says nothing about failure behavior (e.g. invalid or unknown id) or any auth requirements. With annotations doing the heavy lifting, this is adequate but not rich.

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?

One compact sentence with the resource and the returned fields front-loaded; every clause carries information and there is no filler.

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 simple two-parameter read with no output schema, the description covers the essentials by naming the returned fields. It falls short of complete only in omitting error/edge-case behavior for an unknown id.

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%, so both 'id' and 'return_preview' are already documented, including an example value and the default for return_preview. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

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 gives a specific verb ('Get') and resource ('image on BasePic by its id') and enumerates what is returned (links, size, dimensions, type), so the agent knows exactly what the call produces. It does not explicitly contrast itself with the write-oriented siblings (upload_image, edit_image, delete_image), which keeps it short of a 5.

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?

Usage is only implied: the phrase 'by its id' and the id description ('returned by upload_image or edit_image') signal this is the retrieval step after an upload or edit. There is no explicit when-to-use statement, no note about when not to call it, and no named alternative.

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?

Adds substantial context beyond the annotations: a 50 MB size cap, the privacy model ("only people with the link can see it"), and the fact that a delete_key is issued — a security-relevant detail no annotation conveys. The annotations already cover read/write and open-world status, and the description does not contradict them.

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?

Front-loaded with purpose and return values, then constraints, then the edge-case fallback — a sensible reading order with no filler. The curl workaround is slightly long, but it carries information the agent cannot get elsewhere.

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 fully discharges the burden of explaining return values (three URLs, an id, a delete_key) as well as size and privacy constraints. Nothing an agent needs in order to call it correctly is missing.

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 baseline is 3, but the description genuinely enriches the schema: it broadens `url` beyond "public https link to the image" to include X/Instagram/Facebook posts, and clarifies why a filesystem path is not an acceptable value. `return_preview` and `filename` are left to the schema's own descriptions.

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 (upload an image to BasePic) and enumerates exactly what comes back: page_url, image_url, download_url, plus an id and delete_key. It also names the sibling it feeds (edit_image), so an agent can place it in the workflow without opening other schemas.

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?

Explicitly branches input: "Give either a public url ... or image_base64", and spells out the important negative case — a local path or file:// does not work as url, with a concrete curl fallback. It doesn't cover when to prefer get_image/delete_image over this, but the create-vs-read distinction is self-evident from the verb.

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