Oh My Share

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

Goes well beyond annotations by disclosing consequences (share URL stops working immediately, content cannot be restored), auth/ownership prerequisites, and the failure mode for non-owned ids. Annotations already flag destructive/idempotent, so this is pure added value.

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?

Four short sentences, front-loaded with the action and its irreversibility, followed by prerequisites and the sibling pointer. 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?

Single required parameter, no output schema, and annotations already carry the safety profile. The description covers consequences, prerequisites, and id sourcing, so nothing needed 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 the id format and provenance are already documented in the schema. The description reinforces ownership semantics but adds little syntax beyond what the schema provides; 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 (permanently delete) plus resource (your own asset by id), and adds scope constraints (ownership, single-id only). An agent can immediately distinguish this from siblings like view or search_gallery.

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?

Provides real routing guidance: use list_assets to obtain the id, and notes there is no bulk delete, which implicitly rules out batch workflows. It doesn't enumerate explicit when-not-to-use cases against siblings like view, but the context is clear.

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 cover readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' repeats structured data. However, the description adds genuinely new behavioral context: no auth required, cheap to call, and concrete per-IP rate limits (10 uploads/hour, 500 views/hour) that an agent cannot infer from annotations or the empty schema.

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, zero filler, front-loaded with what is returned before the routing guidance. Every clause carries information.

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 compensates by enumerating the returned fields (version, endpoints, features, rate limits). Combined with the usage routing, an agent has everything needed to decide and call correctly.

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 tool takes zero parameters, which is the baseline-4 case per the rubric. The description correctly implies a no-argument call and adds no misleading parameter guidance, though there is nothing further it could meaningfully 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?

States a specific verb and resource ('Return Oh My Share service metadata') and enumerates exactly what metadata: version, REST/MCP endpoints, feature list, and rate limits. The scope is unambiguous and clearly distinct from the sibling content tools.

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 timing ('use it once at startup to discover capabilities') and names the alternatives for the other case ('use list_assets or search_gallery for actual content'). Nothing about when-to-use or when-not-to-use is left to inference.

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 cover the safety profile (readOnly, idempotent, non-destructive), and the description adds behavioral context beyond them: it requires an API key or signed-in session, and critically discloses that results are capped at 50 with no pagination. That cap/auth disclosure is exactly the kind of non-obvious constraint annotations cannot express.

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 tight sentences, front-loaded with scope and ordering, then constraints, then sibling routing. No filler; every clause carries actionable information.

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 and no parameters, the description compensates fully by naming returned fields, the 50-item cap, absent pagination, and auth requirements. An agent has everything needed to call it correctly and interpret its limits.

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?

There are zero parameters, so the baseline is 4. The description does describe the shape of returned items (id, filename, timestamps, share URL), which is useful but concerns output rather than parameters.

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) and resource (assets owned by the authenticated user), plus scope (up to 50, newest first) and returned fields. It explicitly distinguishes itself from siblings by naming search_gallery and view, so an agent can route correctly without opening any 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?

Explicitly tells when to use this tool (own assets) and when to use alternatives: 'Use search_gallery for public works from other users, or view to open one of your assets.' The conditions that select each sibling are named, not implied.

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 cover read-only/idempotent/non-destructive, but the description adds genuinely new context: 'No auth required', the paginated return shape (items, total, page, pages), and the per-item fields. The limit cap and sort semantics duplicate structured data, so it stops short of 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?

Front-loaded with the core purpose, then usage, then return shape, then constraints and alternatives in tight clauses. Every sentence adds a distinct fact with 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?

With no output schema, the description supplies the return contract (pagination fields and item fields) and the auth posture. Combined with 100% schema coverage, an agent has everything needed to call and interpret the result.

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 all four parameters are already documented in the schema (including the query-omission behavior and sort enum meanings). The description restates those meanings in prose without adding format, syntax, or edge-case detail beyond the schema, so 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 (search public gallery works) plus the fields searched (title, description, tags, id) and the browse-without-query fallback. It distinguishes itself from siblings by naming view and list_assets by their distinct jobs.

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 says when to use it ('omit query to browse the newest works') and routes to alternatives with their selecting conditions ('Use view to open a result, or list_assets for your own uploads'). No inference required.

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?

Beyond the annotations, it discloses that each call creates a new asset with no overwrite, that content is public unless password-protected, that assets auto-expire per expiresIn (default 7d, 0 = permanent), and that anonymous uploads are rate-limited to 10/hour/IP. These consequences and limits are exactly the kind of context annotations cannot carry.

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?

Four compact sentences, front-loaded with the outcome and creation semantics before the alternative-tool routing. Every sentence carries distinct information with 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?

With no output schema, the description supplies the return shape (share URL + edit token), plus expiry, visibility, password, and rate-limit behavior. An agent has everything needed to call this correctly and set expectations about the result.

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 the baseline is 3, but the description adds behavioral meaning: password makes the web view prompt before showing content, and expiresIn=0 means permanent with a 7d default. That goes beyond restating the schema field text.

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 first sentence gives a specific verb (upload), resource (HTML or code), and the exact outcome (public share URL plus edit token). It also distinguishes itself from siblings by naming view, list_assets, and delete for the read/list/remove cases.

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?

It explicitly routes the agent to view for reading back, list_assets for owned files, and delete for removal, which is strong when-to-use guidance. It never addresses the remaining sibling search_gallery or states a when-not-to-use condition, so it stops just short of the top score.

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 cover the safety profile (readOnly, idempotent, non-destructive), yet the description goes further: public assets need no auth, password-protected assets return an error carrying the share URL, and client-encrypted content is returned as stored. These are auth, error, and content-fidelity behaviors the structured fields do not supply.

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, front-loaded with the return contract and then the routing plus edge-case behaviors. Every clause carries information and none is redundant.

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?

Although there is no output schema, the description enumerates the returned fields and covers the three edge cases an agent would hit (no auth for public, error for password-protected, as-stored for encrypted). Nothing needed to invoke or interpret the call 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 the single parameter is already documented as a '12-character asset id returned by upload or search_gallery'; the description adds only the bare phrase 'by id'. With the schema doing the heavy lifting, this is the baseline case.

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 ('Fetch a single asset by id') and enumerates exactly what is returned (content, filename, creation time, share URL). It is clearly distinguishable from siblings like search_gallery and list_assets, which the description itself names.

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 routes the agent: 'Use search_gallery to find an id, or list_assets for your own uploads.' This tells the agent when to reach for this tool versus two named alternatives, leaving nothing to inference.

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