Cuttly MCP by usefulapi

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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false. The description adds valuable context beyond annotations: irreversibility, that statistics are also deleted, that links become error pages, that Cuttly cannot restore, no retry behavior, and plan requirement. Strong addition.

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-loads the critical warning (WRITE, IRREVERSIBLE) and is reasonably concise. The raw API URL at the end is somewhat extraneous for an agent but not harmful.

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?

Complete for a destructive one-parameter tool: covers irreversibility, confirmation requirement, plan gating, and retry semantics. No output schema exists but none is needed given the irreversible delete nature.

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 schema fully documents the single 'link' parameter with example. The description does not add format details beyond what the schema provides. 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?

States a specific verb+resource (permanently delete a short link and its statistics) and specifes the blast radius. Clearly distinct from siblings like update_link or set_link_expiration.

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 clear context: requires user confirmation of the exact link, and needs the Single plan or higher. Does not name alternatives (e.g., update_link to disable instead of delete), but provides strong preconditions.

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, openWorldHint and destructiveHint=false, so safety is covered. The description still adds non-obvious behavior: plan-gated date filtering, the per-call quota, and the underlying GET endpoint — useful operational context beyond the annotations.

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?

Compact and front-loaded: the resource and the returned dimensions come first, then the plan/quota constraints, then the endpoint. The long enumeration of dimensions is dense but each item conveys an actual returned field, so little is wasted.

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 carries the return-value burden and does so by listing the stat categories returned (sources, referrers, countries, devices, OS, browsers, brands, languages). It does not describe the response envelope or error cases, which is the main remaining gap.

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 three parameters (link, date_from, date_to) are already documented, including the exact date pattern and the Team-plan restriction. The description's mention of the date-range plan requirement duplicates the schema rather than extending it, landing at the baseline 3.

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+resource ('Click statistics of one short link') and enumerates exactly which breakdowns are returned, so the agent knows the shape of the result before calling. It is clearly distinguishable from the five sibling tools, all of which are mutating link 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?

Adds real selection context: the date-range filter requires the Team plan or higher, and one call counts against a Free-plan limit of 3 per 60 seconds. It does not explicitly name an alternative tool, but since it is the only read/stats operation among its siblings, the routing is unambiguous.

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 real behavioral context beyond annotations: the 'WRITE:' prefix, the plan requirement, and notably 'The call is sent once and never retried', which tells the agent there is no automatic retry. Annotations already cover readOnly/destructive/idempotent, so this is a valuable addition rather than a repeat.

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-loads the operation type and destination concept, then layers in edge cases and prerequisites. Dense but each sentence carries information; the trailing raw endpoint URL is slightly extraneous but harmless.

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 need not cover returns, and it supplies the mutation semantics, prerequisites, and removal path an agent needs. Knowledge of edge behavior like per-device rule overlap is implied rather than fully spelled out, keeping it from a 5.

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. The description clarifies the remove/destination mutual exclusivity and restates the 'redirect' platform meaning, but both of these are already present in the schema descriptions, so it adds little beyond structured data.

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 ('send visitors ... to another destination') and resource (device redirect rules), and even names the WRITE nature up front. The purpose is unambiguous and distinguishable from siblings like shorten_link or update_link, though it never explicitly names which sibling handles related-but-different 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?

Gives concrete when-to-use guidance: 'Set remove: true instead of a destination to delete the rule' explains the deletion case, and 'Needs the Single plan or higher' states a prerequisite. It does not compare against siblings, so it falls short of explicit alternative 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 destructive=true and idempotent=true, so the description leans on real added context: the plan entitlement gate, the post-expiration redirect behavior, and the operational note that 'the call is sent once and never retried'. It stops short of rate limits or a rollback/reversibility statement, but the retry and entitlement details are genuinely beyond the annotations.

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?

Six sentences, front-loaded with the WRITE label and the core action, then prerequisites and mode behavior. The trailing raw 'GET https://cutt.ly/api/api.php?edit=...&expire=...' is arguably noise for an agent choosing a tool, but it is short and the rest is efficient.

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 destructive mutation with no output schema, the description supplies the safety-relevant context an agent needs: entitlement requirement, non-retry guidance, and what happens to visitors after expiry. Return-value details are absent, but with no output schema declared that is a minor gap.

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 every parameter including the mode enum, date pattern, and click bounds is already documented. The description restates mode semantics ('none' removes an existing expiration) without adding new syntax or format detail, which is the expected baseline when the schema carries the load.

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?

Opens with an explicit 'WRITE:' marker and states a specific verb+resource: 'set or remove the expiration of a short link'. The scope (clicks or date based expiration, with an optional post-expiration redirect) is unambiguous and clearly separated from the other link-management siblings.

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 concrete preconditions (needs the Single plan or higher) and clarifies that mode 'none' removes an existing expiration rather than creating one. It does not explicitly route the agent between this tool and cuttly_update_link for overlapping edits, which is the only missing piece.

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?

Goes well beyond the annotations by disclosing that each call consumes the monthly link quota, gives concrete per-plan rate limits (Free 3/60s, Starter 6, Single 60), and states the call is sent once and never retried. Alias-collision failure behavior and the return payload are also described, which is rich, decision-relevant context for a non-idempotent write.

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 write marker, purpose and limits are front-loaded and the content is dense but useful. The trailing 'GET https://cutt.ly/api/api.php?short=...' fragment is an incomplete, low-value URL snippet that slightly muddies an otherwise tight description.

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 correctly covers return values (short link, full link, page title), quota and rate-limit behavior. The only shortfall is the dangling endpoint fragment and no guidance on how this tool relates to cuttly_update_link for an existing link.

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 schema already documents url, alias, public_stats and use_branded_domain. The description only reinforces the alias concept ('the part after the slash') and adds no syntax or format detail beyond the schema, 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 ('create a Cuttly short link for a long URL') plus the optional custom alias. The verb 'create/shorten' cleanly separates it from the sibling mutation tool cuttly_update_link and the read tools (stats), so an agent can route without opening the 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?

The 'WRITE:' prefix and the quota/rate-limit notes imply when the tool is applicable, but there is no explicit when-not or named alternative (e.g. 'use cuttly_update_link to change an existing link instead of creating a new one'). Usage context is implied rather than stated.

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?

Goes well beyond the annotations by disclosing consequences the hints cannot convey: alias changes break the old short link, destination changes redirect all visitors immediately, the plan gate, that no previous values are returned, and that the call is never retried. This is exactly the destructive-operation context an agent needs before mutating a live link.

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 WRITE marker and the affected resource, then layers optionality, side effects, plan gate, and safety caution in tight sentences with no filler. Every clause carries decision-relevant 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?

For a 6-parameter destructive mutation with no output schema, the description covers the mutation semantics, plan constraints, irreversible side effects, and even the return-value expectation ('sends no previous values back'). Nothing essential for correct invocation 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 description coverage is already 100%, so baseline is 3, but the description adds real semantic weight beyond the schema: the alias side effect ('old short link stops working'), the instantaneous global redirect behavior, and the instruction to send only changed fields. The unique-click window semantics remain schema-only.

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?

Opens with an explicit verb and resource ('WRITE: change a short link') and enumerates exactly which fields are mutable (alias, destination URL, title, tag, unique-click window). This is distinguishable from siblings like cuttly_delete_link or cuttly_set_link_expiration, which target different 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?

Gives clear operating conditions: 'Send only what you want to change,' the Single-plan requirement for editing, and a caution to 'ask the user before you change a live link.' It does not explicitly name a sibling alternative or exclusion, so it stops short of full when/when-not routing.

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