kyde score

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds meaningful behavior beyond them: no signup required, key scoping semantics via service.name, and that the webhook receives an HMAC-signed POST on band changes. It does not say whether the returned key is shown only once or whether creation is idempotent.

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 the key facts front-loaded: identity, scope, then the optional parameter. Nothing is padded, though the fragment style ('(no signup)') reads slightly like marketing rather than specification.

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 creation tool with no annotations gaps and full schema coverage, the description is mostly sufficient, but it never says what the call returns — presumably the key/secret value — which is the single most important thing an agent needs, especially if the key is only displayed once. No output schema exists to cover this.

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 documented, so baseline is 3; the description earns above baseline by explaining what the webhook actually does (HMAC-signed POST on band change) and that it is recommended, not merely optional. It does not add format/validation detail beyond the https note already in the 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 and resource ('Create a scoring key') and adds a distinguishing constraint ('no signup') plus the key's scope ('One key covers all agents, identified by OTel service.name'). It is clear apart from the sibling set, though it does not explicitly contrast with revoke_key or set_webhook.

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?

Useful context is implied — one key per service.name, webhook optional but recommended — but there is no explicit guidance on when to call this versus set_webhook (which presumably attaches a webhook later) or whether the webhook can be added post-creation. The agent must infer.

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?

The readOnlyHint already establishes that this is a safe read operation, so the description appropriately focuses on domain behavior. It adds useful context by defining the 0-39/40-69/70-100 score bands and the 'learning' state until the 30-run baseline freezes, which an agent could not infer from annotations alone.

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 compact sentence with the primary subject front-loaded and no wasted wording. Score thresholds and learning-state semantics are packed efficiently into the same sentence.

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, single-optional-parameter read tool with annotations covering safety, the description supplies the essential domain semantics: score ranges, status meaning, and per-agent scope. It could go slightly further in describing the exact return structure, but it is complete enough for correct invocation.

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 schema itself explains that the key can be omitted when sent as an x-kyde-key header. The description mentions 'under the key' but adds no syntax or format details beyond the schema, so the baseline of 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 clearly states that it returns current drift scores per agent under a key, and it explains the score bands and learning status. It does not explicitly distinguish itself from the sibling key-management tools, but the resource and scope are specific enough for an agent to understand what it does.

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 explains how to interpret returned scores but gives no explicit guidance on when to call this tool, when not to, or how it relates to alternatives. Usage is only implied by the resource being a drift score read.

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 readOnlyHint=false, so the description's added value is specifying exactly what is destroyed — all data stored under the key — and that the effect is permanent. That is the key behavioral fact an agent needs before calling. It stops short of stating irreversibility guarantees, auth scope, or whether any grace period exists.

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, and the destructive consequence is front-loaded ahead of the mechanical prerequisite.

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 two-parameter mutation with no output schema and strong annotations, the description covers effect, permanence, and the confirm gate. Only authentication expectations and the exact failure behavior of confirm=false are left unstated, which are minor gaps here.

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 key parameter is documented in the schema (including the x-kyde-key header fallback), while confirm is a bare boolean. The description compensates for the undocumented parameter by stating 'Requires confirm=true', which is the one fact that matters. Baseline 3 fits given the partial 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 (revoke) and resource (the key), plus the consequential scope: all data under it is deleted. It does not explicitly name create_key as the inverse, but the purpose is unambiguous against the sibling set.

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 gives the confirm=true prerequisite, which is real usage guidance, but never says when to choose this over alternatives or when not to use it. The revoke-vs-create contrast is only inferable from the tool name and sibling list.

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 idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the description's job is lighter. It does add value by stating the webhook must be https and that it is triggered by band changes, but it never says whether an existing webhook is overwritten or whether only one webhook can exist at a time.

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 front-loaded sentence with no wasted words; the action and trigger are stated immediately.

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, non-destructive, idempotent mutation with no output schema, the definition is minimally adequate but leaves open whether a prior webhook is replaced and what the call returns or errors on.

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%: 'key' is documented in the schema while 'webhook_url' is a bare string, and the description partially compensates by implying the URL must be https. The description adds no detail on the key parameter's role given the schema already covers the header alternative.

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?

Clear verb+resource: 'Add or change the https webhook notified on band changes' tells the agent exactly what is being configured and the event it fires on. It is not confused with the sibling key/score tools, though it never explicitly differentiates itself from 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?

'Add or change' implies both create and update usage, but there is no explicit statement of when to use this versus alternatives (there are none listed), nor any prerequisites such as needing an existing key.

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