Search, read and organize the screenshots in your ScreenVerb cloud library.
Scored across 5 tools
Each tool has a distinct action-resource pairing: list browses, search filters, get retrieves one item, rename updates filename, and delete removes the item. The descriptions explicitly clarify the list-vs-search boundary and when to use get after search.
All tools follow a consistent snake_case verb_noun pattern with the same singular resource noun, screenshot. The naming is predictable and easy to scan.
Five tools are well-scoped for managing a screenshot library: browse, search, view, rename, and delete. Each tool earns its place without unnecessary surface area.
The set covers listing, searching, retrieving, renaming, and deleting existing screenshots, but lacks a create/upload operation and cannot edit caption, tag, or label metadata despite search depending on those fields. These are notable gaps for full lifecycle management, though agents can still work with existing screenshots.
Remove a screenshot from the signed-in user's cloud library. Its stored image is retained. Ask the user to confirm before calling this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Screenshot id returned by list_screenshots or search_screenshots. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| deleted | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds a genuinely non-obvious semantic: the stored image is retained, so only the library entry is removed. It also adds the human-confirmation requirement, which no annotation conveys. It stops short of saying whether the record deletion itself is reversible or what an error returns.
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, each carrying distinct load: what it does, the surprising retention behavior, and the confirmation requirement. Front-loaded with the action, zero redundancy.
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 destructive tool with rich annotations and an output schema, the description covers the essentials an agent needs: scope, the retention caveat, and the confirm-first rule. The only gap is irreversibility of the record removal itself.
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 single `id` parameter is fully documented in the schema (including its source, list_screenshots/search_screenshots). The description adds nothing about the parameter, so the baseline of 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?
States a specific verb and resource ("Remove a screenshot") plus scope ("from the signed-in user's cloud library"), which cleanly separates it from the read-only siblings (get_screenshot, list_screenshots, search_screenshots) and from rename_screenshot.
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 an explicit precondition — "Ask the user to confirm before calling this tool" — which is exactly the gating rule an agent needs for a destructive call. It does not name an alternative action (e.g., what to do if the user wants to keep the record), so it falls short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show one screenshot from the signed-in user's cloud library: the image itself, its metadata with up to 1,200 characters of OCR text, and a temporary image URL.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Screenshot id returned by list_screenshots or search_screenshots. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| name | Yes | |
| tags | Yes | |
| width | Yes | |
| height | Yes | |
| message | Yes | |
| metadata | Yes | |
| image_url | Yes | |
| share_url | Yes | |
| created_at | Yes | |
| size_bytes | Yes | |
| content_type | Yes | |
| thumbnail_url | Yes | |
| image_included | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, non-destructive, closed-world operation, so the description is not burdened with safety disclosure. It usefully adds behavior beyond annotations: the data is scoped to the signed-in user's cloud library, OCR text is capped at 1,200 characters, and the image URL is temporary.
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 with a colon-separated list of key return elements. It is appropriately sized for a simple read-by-id tool and contains 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 one-parameter read tool with annotations and an output schema, this description is complete enough: it identifies the signed-in-user scope and summarizes the image, metadata/OCR, and temporary URL. Error cases are not described, but the structured fields and output schema cover the remaining contract.
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 the single id parameter is already well documented as coming from list_screenshots or search_screenshots. The description adds no parameter-specific semantics beyond saying it shows one screenshot, so baseline 3 is appropriate.
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 clear verb and resource: 'Show one screenshot' from the signed-in user's cloud library, and it specifies the return contents. It implicitly distinguishes retrieval from list/search/delete/rename by emphasizing a single screenshot, but it does not explicitly name sibling tools or contrast them.
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 say when to use this tool versus alternatives such as list_screenshots or search_screenshots, nor does it state when not to use it. The only routing hint is in the input schema's id field, not in the description itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the signed-in user's cloud screenshots with compact metadata. Use this to browse recent screenshots or page through the library; use search_screenshots to filter, and get_screenshot to view one.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Result order. Defaults to newest. | |
| limit | No | Maximum number of screenshots to return, 1 to 50. Defaults to 20. | |
| cursor | No | Pass next_cursor from the previous response to get the next page. Use the same sort as that request. |
| Name | Required | Description |
|---|---|---|
| next_cursor | Yes | |
| screenshots | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds two useful behavioral facts beyond that: results carry only compact metadata, and the tool supports paging through the library. It stops short of describing ordering defaults or page-size behavior, which the schema covers instead.
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?
Two sentences with no filler, and the primary purpose is front-loaded. However, the second sentence packs three clauses (browse, filter alternative, view alternative) into one semicolon chain, which is slightly dense for the amount of routing information it carries.
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 a simple read-only list with three optional, fully documented parameters, an output schema, and annotations covering the safety profile. The description covers what to call it for, what it returns at a high level, and where to go instead, so nothing an agent needs 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% and each parameter's enum, bounds and defaults are documented in the schema, so the description is not required to compensate. It only hints at paging semantics via 'page through the library' and adds no sort or cursor detail beyond what the schema already states, 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?
States a specific verb (List) plus the resource and scope (the signed-in user's cloud screenshots) and notes the payload is compact metadata. It explicitly names the two sibling tools it is not, so an agent can distinguish it from search_screenshots and get_screenshot without opening a 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 use cases (browse recent screenshots, page through the library) and routes filtering to search_screenshots and single-item viewing to get_screenshot. The when-to-use versus alternatives split is fully spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the filename of a screenshot in the signed-in user's cloud library. This keeps its share link unchanged.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Screenshot id returned by list_screenshots or search_screenshots. | |
| name | Yes | New filename, up to 160 characters. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| name | Yes | |
| updated | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare non-read-only, idempotent, non-destructive and closed-world. The description adds a genuinely useful behavioral fact beyond them: the share link is preserved across the rename. It omits edge behavior such as name collisions or validation failures, which keeps it below 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?
Two short sentences with zero filler; the operation and scope come first and the share-link guarantee follows as a supporting note.
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?
An output schema exists and annotations cover the safety profile, so the description needn't explain return values. For a two-parameter rename it is essentially complete, with only failure-mode semantics left unstated.
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%, with both `id` (where to obtain it) and `name` (160-char limit) documented in the schema. The description adds no syntax, format, or constraint detail beyond that, 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?
States a specific verb and resource ('Update the filename of a screenshot') plus the scope ('signed-in user's cloud library'), which is enough to separate it from get/list/search/delete siblings. It does not explicitly name those siblings as alternatives, so it stops short of full differentiation.
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 establishes context (the user's own cloud library) but never says when to prefer this over alternatives or what prerequisites must hold (ownership, existing id). Usage is implied rather than guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the signed-in user's screenshots by filename, OCR text, caption, tag or label, optionally within a time range. Use this when the user asks to find a screenshot, then call get_screenshot to view it.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Result order. Defaults to newest. | |
| time | No | Limit to screenshots taken in the last 24 hours (today), 7 days (week) or 30 days (month). Defaults to all. | |
| label | No | Exact tag or AI label, case-insensitive, for example a value from a previous result's tags or labels. | |
| limit | No | Maximum number of screenshots to return, 1 to 50. Defaults to 20. | |
| query | No | Words to find in the filename, OCR text or caption. Every word must match. | |
| cursor | No | Pass next_cursor from the previous response to get the next page. Use the same sort as that request. |
| Name | Required | Description |
|---|---|---|
| next_cursor | Yes | |
| screenshots | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so safety is covered; the description adds useful scope information by saying results are limited to the signed-in user's own screenshots and by enumerating which content is indexed for matching. It says nothing about result ordering defaults or pagination behavior, though the cursor parameter and output schema partly cover that.
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?
Two tight sentences with no waste, front-loading what is searched before the usage/chaining hint.
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 an output schema and full annotation coverage, the description supplies enough to invoke correctly: scope, searchable fields and the follow-up step. Only minor gaps remain, such as what happens on zero matches versus pagination.
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 defaults, enums, limits and cursor semantics are all documented in the schema already. The description only restates the searchable fields at a high level and adds no syntax, matching, or combination guidance beyond what the properties say.
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?
A specific verb (search) plus resource (the signed-in user's screenshots) plus the searchable fields (filename, OCR text, caption, tag, label). It is easy to tell apart from get_screenshot thanks to the explicit 'call get_screenshot to view it', but it never distinguishes itself from the sibling list_screenshots, which covers similar ground.
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 a clear trigger ('when the user asks to find a screenshot') and the natural follow-up call (get_screenshot). It lacks explicit when-not guidance or a stated alternative such as list_screenshots for unfiltered browsing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
delete_screenshotget_screenshotlist_screenshotsrename_screenshotsearch_screenshotsSearch, read and save to your private vault of images, links and notes.
Search and organize your reading library of highlights, saved articles, notes and tags.
Search, read, and write highlights, notes, screenshots, collections, projects, and tags in Gleanit.
Search and read Speechyou voice notes and meeting transcripts with secure OAuth access.
Add one secure layer between your agents and this server.
