Dead Man's Snitch MCP by usefulapi

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds value beyond them: 'keeping the existing ones' confirms the additive/non-destructive merge semantics, and 'Returns the snitch's full tag list' discloses the return shape despite there being no output schema. It does not mention auth requirements or tag-limit behavior.

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 the write nature and additive semantics front-loaded, followed by the return contract and the underlying endpoint. Zero 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 two-parameter additive write with no output schema, the description covers the safety profile, the merge behavior, and the return value. Remaining gaps (tag validation rules, whether duplicates are deduplicated, permission requirements) are minor given the annotations and schema constraints.

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 50%: the 'snitch' parameter is well documented (token, masked token, or exact name), while 'tags' items carry only the placeholder text 'A tag.' The description names both parameters but adds no format, duplication, or limit guidance beyond the schema, so it does not compensate for the thin half of the coverage.

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 (add), resource (tags on a snitch), and scope (keeping existing ones), which cleanly separates it from the sibling deadmanssnitch_remove_tag. An agent can pick the right tool 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 'keeping the existing ones' frame the operation as additive, implicitly distinguishing it from deadmanssnitch_remove_tag. However, there is no explicit when-to-use or when-not-to-use guidance, and no mention of how this relates to deadmanssnitch_update_snitch, which may also touch tags.

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=false, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior language: the 402 failure when the plan's snitch limit is reached, plus the operational requirement to keep the check-in URL secret and call it each run. It stops short of noting that repeat calls create duplicate snitches.

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?

Roughly three short sentences, with the WRITE marker and resource front-loaded and no filler. The trailing endpoint notation is compact and informative rather than padding.

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 explains what is returned (the snitch and its check-in URL) and one failure mode. Auth/prerequisite and duplicate-creation behavior are unstated, leaving a small gap for a 6-parameter mutation tool.

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 83% with two enums documented in-schema, so the parameters are largely self-explanatory. The description adds no parameter-level meaning (e.g., how interval interacts with plan limits) beyond what the schema already states, which is the expected 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?

States a specific verb and resource ('create a new snitch (monitor)') and disambiguates it from the sibling read/update/pause tools by labeling it WRITE. The postcondition (returns the snitch with its check-in URL) further pins down what the tool produces.

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 context is implied by 'WRITE: create' among siblings and by the explanation that the returned URL must be called on every run, but there is no explicit when-to-use/when-not guidance or routing to alternatives such as deadmanssnitch_update_snitch for changing an existing snitch.

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 destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: the response contains a sensitive check-in URL that acts as a credential, plus the underlying GET /v1/snitches/{token} semantics. It does not cover not-found or invalid-token behavior, 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?

Two tightly written sentences that front-load what is returned and then the security caveat. The trailing 'GET /v1/snitches/{token}' is arguably implementation detail an agent does not need, but it is brief and 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?

There is no output schema, so the description carries the burden of return values and it does so by naming the full-detail payload and the key field returned. What remains missing is any failure-mode behavior for an unknown token or name.

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 schema already explains that the argument accepts a token, masked token, or exact name. 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+resource ('One snitch with its full details') and explicitly contrasts with the sibling list tool by emphasizing a single record and its complete payload. An agent can distinguish it from deadmanssnitch_list_snitches without opening either 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?

Usage is implied by the framing ('one snitch with its full details'), but there is no explicit when-to-use statement, no prerequisite call-out, and no named alternative such as list_snitches for bulk retrieval. The guidance about sharing the URL is a security caution, not selection guidance.

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 readOnly/destructive annotations: it discloses that tokens are masked, why masking matters (the token is the check-in secret), that the API is unpaged so all snitches are returned, and enumerates the returned fields. These are exactly the operational facts an agent needs before calling.

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 tight sentences ordered from what it lists, to downstream usage, to paging behavior, to filtering, ending with the HTTP endpoint. No filler and nothing important buried.

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 naming the returned fields (status, interval, alert type, tags, last check-in). Combined with the masking and no-paging notes, 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% and the schema already documents both parameters, including that tags must ALL match and the status enum values. The description repeats the filter semantics without adding format or behavioral 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 ('List the snitches') and even glosses the domain term as 'cron/heartbeat monitors', so an agent unfamiliar with Dead Man's Snitch understands what is being listed. It is clearly distinguished from the singular sibling get_snitch.

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?

Tells the agent how to chain: 'pass the masked token or the name to the other snitch tools', which routes to get/pause/update/etc. It also states filtering is optional and that no paging exists, so the agent knows a single call returns everything. It does not explicitly say when to prefer get_snitch over this, so it stops short of full when/when-not coverage.

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 destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description earns credit by disclosing the non-obvious consequence (alerts are silenced, so a dead job goes unnoticed) and the `until` state machine plus the pending-snitch failure mode. It doesn't mention the response payload, but with no output schema that is a small gap.

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 write classification and the core effect, then folds semantics, precondition, and endpoint into the same tight block. Every clause carries information; nothing is padding.

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 mutation with no output schema, the description supplies the safety consequence, the resume-state semantics, the blocking precondition, and the underlying endpoint. Nothing an agent needs to call this 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. The description goes beyond by explaining what 'unpaused' actually means operationally (stays paused until deadmanssnitch_unpause_snitch is called) and confirming 'healthy' as the default resume point, detail the schema's enum-less string description leaves implicit.

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 (pause) and resource (snitch) and immediately qualifies the scope with 'WRITE' and 'SILENCES its alerts'. The alert-silencing framing is what separates it from sibling unpause_snitch and get_snitch without the agent needing to open 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?

Gives explicit when (silence a job's alerting), what happens if you don't (a stopped job goes unnoticed), the alternative route back (deadmanssnitch_unpause_snitch via 'unpaused'), and a concrete exclusion: a pending snitch that has never checked in cannot be paused. That covers use, alternative, and when-not in three clauses.

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 destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds value beyond that by clarifying the blast radius (only the tag is removed, not the snitch) and the return payload ('Returns the remaining tags'), 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 tight fragments, front-loaded with the WRITE classification and the scope qualifier before the endpoint. Every clause carries information; nothing is padding.

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 states the return value and covers the mutation's scope, while annotations carry the safety profile. Minor gaps remain around error behavior (e.g., removing a nonexistent tag from an idempotent endpoint), but nothing essential to 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 100%, so both parameters are fully documented in the schema, including the flexible snitch token/masked-token/name forms. The description adds nothing beyond confirming token and tag are path segments via the DELETE route, 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 one tag from a snitch) and immediately scopes it: 'the snitch itself is untouched.' This distinguishes it from the sibling add_tags and from destructive snitch-level operations 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?

The 'WRITE:' prefix signals this is a mutation, and 'the snitch itself is untouched' preempts a common misuse. However, it never states when to reach for this over add_tags or what prerequisite state is needed (e.g., tag must currently exist), leaving usage implied rather than explicit.

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=false, idempotentHint=true, destructiveHint=false and openWorldHint=true. The 'WRITE:' prefix and 'safe on a snitch that is not paused' clause are consistent with those hints and reinforce idempotency in plain language, but add little beyond what the annotations already 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?

A single compact line with the WRITE nature and safety note front-loaded, followed by the endpoint. No filler sentences.

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 single-parameter mutation tool with full annotation coverage and no output schema, the description supplies the action, the safety characteristic, and the underlying endpoint. Nothing essential is missing, though the effect on the snitch's alerting state could be spelled out slightly more.

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% for the single 'snitch' parameter, and the schema already explains it accepts a token, masked token, or exact name. The description adds no additional parameter meaning, 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+resource: 'resume alerting for a paused snitch', which clearly contrasts with the sibling deadmanssnitch_pause_snitch. It does not explicitly name the sibling, so it falls just short of the top mark, but the operation 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?

It notes the operation is 'safe on a snitch that is not paused', which implies you need not check state first, but there is no explicit when-to-use guidance, no prerequisites (e.g. auth scope), and no routing to alternatives such as pause_snitch or create_snitch.

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 destructiveHint=true and idempotentHint=true, and the description adds genuinely new behavioral context on top: patch-style partial updates, that `tags` overwrites the entire list, that an empty `alert_email` reverts alerts to all team members, and that the response returns the snitch with its token masked.

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, each carrying distinct information, with the write/partial-update constraint front-loaded and the destructive tag-replacement caveat immediately after. 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?

No output schema exists, yet the description tells the agent what comes back (updated snitch, masked token) and covers the mutation's irreversibility for tags. Combined with 100% schema coverage and full annotations, nothing an agent needs to call this 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 baseline is 3; the description earns above that by clarifying cross-parameter semantics the schema does not convey (tags is a full replacement, empty alert_email means all team members). It does not, however, speak to the interval/alert_type enums, which 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?

States a specific verb and resource ('WRITE: change a snitch') and pins the operation to PATCH /v1/snitches/{token}. It also explicitly distinguishes itself from the sibling deadmanssnitch_add_tags, so an agent can route without opening either 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 the operative semantics ('Only the fields you pass change') and names the alternative plus the condition that selects it: use deadmanssnitch_add_tags to add tags rather than replacing the list here. Both the when and the when-not are present.

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