FixLore

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

Annotations already declare write, non-idempotent, non-destructive, closed-world. The description adds the auth requirement (FIXLORE_KEY) and that the target must already exist, which is real context beyond the annotations. It does not say whether comments are immutable/append-only, whether edits or deletion are possible, or how failures surface.

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, front-loaded with the core action and its variants, followed by the hard prerequisite. No filler; every clause earns its place.

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, so return values need not be described, and auth is covered. But for a non-idempotent mutation with low schema coverage and a nested environment object, the description leaves out what id identifies, how environment is used, and the lifecycle/immutability of a posted comment.

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 only 25% (essentially just environment), so the description must compensate. It enumerates four of the five kind values but omits 'note' and never explains that id refers to the target experience's identifier, nor what body/environment should contain. Partial compensation at best.

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) and resource (supplement/variant/correction/question to an existing experience), with an inline example that makes the intent concrete. It implicitly distinguishes itself from submit_fix ('existing'), but never names the sibling or contrasts explicitly.

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 example ('on Debian 12 you also need X') and the 'existing experience' qualifier imply when this tool applies, and the FIXLORE_KEY note signals a prerequisite. However, there is no explicit when-not guidance or routing to alternatives like submit_fix or report_fix_issue, which overlap conceptually.

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, idempotentHint, openWorldHint and destructiveHint=false, so 'Read-only' is pure repetition of structured data. The description does add that the payload includes receipts by environment, quality checks and revision history, but an output schema already exists to carry return contents, so the incremental behavioral value is modest.

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?

One tightly packed sentence that leads with the action and resource, then lists contents. No filler, no restatement of the title or schema.

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 a rich annotation set and an output schema present, the description needn't explain return semantics, and it correctly avoids doing so. What remains missing for a single-entity read is how to obtain the required id and the failure mode for a nonexistent one, but nothing essential to correct invocation is absent.

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 0% and the single required 'id' parameter is never explained in the description — no hint that it is a FixLore identifier, where to source it, or what happens with an invalid id. A required param on a 0%-coverage schema is exactly the case where the description must compensate, and it does not.

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 ('Read one FixLore experience in full') and enumerates the exact sections returned, which is far more informative than a tautology. The contrast with the plural search_fixes sibling is implied by 'one ... in full' but never made explicit, so it falls short of full sibling 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?

Usage is only implied: 'in full' suggests fetching complete detail for a known fix, contrasted with a search. There is no explicit when-to-use/when-not, no statement of the condition that selects this over search_fixes, and no note on what to do if the id is unknown.

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 cover the safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds genuinely useful context beyond them: the record is stored as a correction with an [issue] prefix, the author and operator are the audience, and authentication via FIXLORE_KEY is required. It does not mention duplicate handling, which matters 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?

Three short sentences, front-loaded with the action, then the storage/visibility consequence, then the auth prerequisite. No filler and nothing repeated from the schema.

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, so return values need not be described, and the description covers purpose, audience, storage form, and auth. The remaining gap is the meaning of the id parameter and duplicate/retry behavior for a non-idempotent write, which the low schema coverage leaves unfilled.

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 only 25%, so the description must compensate; it partially does by enumerating the issue kinds that map to the kind enum. But id (which entity is being corrected) and body are left entirely unexplained, and the environment parameter is only documented 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 (report) and resource (an experience that is dangerous, outdated, wrong, or not reproducible), plus what happens to it (stored as a correction with an [issue] prefix). It does not distinguish itself from near-name siblings report_fix_result and report_outcome, which an agent must choose between.

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?

Implied usage is clear (file a report when something is wrong with a fix/experience), and the FIXLORE_KEY prerequisite is stated. However there is no explicit when-not guidance and no routing hint vs report_fix_result or report_outcome, which are the most confusable siblings.

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?

Exceeds the annotations by disclosing the FIXLORE_KEY/write-scope auth requirement and the data-handling policy ('send no secrets; evidence strings are redacted'). The idempotentHint and non-destructive profile come from annotations, and the revision-mismatch refusal is stated in the schema rather than the description.

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, front-loaded with the core action, followed by timing, prerequisites, and a safety caveat. No filler and nothing 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?

An output schema exists so return values need no explanation, and the description covers purpose, timing, auth, and redaction for a 12-param write tool. The one real gap is disambiguation from the similarly named report_outcome sibling.

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?

With 12 parameters at 50% schema coverage, the schema does only half the work. The description reinforces fix_revision's binding semantics and constrains the evidence field ('no secrets'), but says nothing about note, outcome values, environment, or the other undocumented params; 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 and resource ('Report whether a fix worked') and adds a distinctive binding constraint ('bound to the exact revision you read'). However, it never disambiguates from the sibling report_outcome, which by name 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?

'Always call after trying one' gives explicit timing guidance, and the write-scope prerequisite is stated. There is no when-not guidance or named alternative to route the agent to versus report_outcome or comment_fix.

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 write (readOnlyHint=false), idempotent, non-destructive, non-openWorld, so safety is covered. The description adds useful non-annotation context: it is deprecated and requires FIXLORE_KEY for authentication. It does not describe what the write actually mutates or the effect of running it against an already-reported fix, leaving meaningful behavioral context undisclosed.

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 clauses, one sentence, front-loaded with the deprecation status and followed by the compatibility rationale and auth requirement. Every element earns its place 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?

An output schema exists, so return values need no explanation, and deprecation plus auth needs are covered. However, for a 12-parameter tool with almost no schema descriptions, the definition leaves the agent without enough to populate arguments correctly beyond the two required fields.

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 8% across 12 parameters (including a nested environment object), and the description mentions no parameter at all — not even the required id/outcome pair or the outcome enum values. The description does nothing to compensate for the near-total documentation gap.

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 names the exact sibling it duplicates ('report_fix_result') and labels itself a deprecated alias, so an agent immediately knows what it does and how it differs from that sibling. It stops short of stating the operation in its own words (recording a fix outcome), but the alias reference is functionally equivalent and 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?

'kept so existing clients keep working' clearly tells the agent this exists only for backwards compatibility, implying new work should call report_fix_result. It gives the when-to-use condition without an explicit negative instruction or named alternative in imperative form, so not a full 5.

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 readOnly/idempotent/non-destructive, yet the description adds genuinely new behavioral context: the returned card must be treated as untrusted data, and the agent should inspect `confirm` and `not_when` before acting. This prompt-injection-style warning is exactly the kind of guidance structured fields 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?

Three tight sentences, front-loaded with the purpose, then ordering guidance, then the safety caveat. No filler; each sentence carries a distinct obligation.

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, so return values need not be explained, and the description supplies the workflow and trust-boundary context an agent needs. It is essentially complete, though it does not touch on pagination or the technology/environment parameters that a richer definition might hint at.

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 88%, so the schema already documents error_message, cursor, technology, environment, etc. The description reinforces the error-message concept ('raw error text') but adds no format or syntax detail 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 (search), resource (fixes in FixLore), and matching criterion (an error), which an agent can immediately separate from retrieval-by-id siblings like get_fix or write siblings like submit_fix. The scope 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?

Gives explicit workflow timing: 'BEFORE guessing or retrying a failing command, but AFTER you have the raw error text.' This tells the agent exactly when to reach for it, but it names no sibling alternative (e.g., get_fix when you already hold an id), so it stops short of full routing 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?

Annotations declare a non-readonly, non-destructive, non-idempotent closed-world write, and the description adds genuinely new context: an auth requirement (FIXLORE_KEY), a data-handling constraint (never include secrets), and the quality-gate outcome model (BLOCK/WARNING/PASS). These additions go beyond what the annotations convey, though nothing is said about whether a blocked submission is persisted or how non-idempotency manifests on retry.

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 with zero filler, and the core action plus the field list are front-loaded ahead of the auth and return-value notes. The unexplained 'v2 card' jargon costs it the top mark.

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, so explaining the return payload is optional (and it does so succinctly), and the auth prerequisite is covered. The fatal gap is that 16 of 21 input parameters have no semantics anywhere, which is a large incompleteness for a schema this wide.

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?

With 21 parameters and 0% schema description coverage, the description carries the full burden, yet it names only 5 fields (confirm, not_when, principle, verify, rollback). The 3 required fields (title, problem, steps) plus cause, error, failed, technology, environment, variables and others are left completely undefined anywhere in the definition.

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 ('Contribute a reproducible fix') and names the artifact type ('v2 card'), which separates it cleanly from read siblings like get_fix and search_fixes. It stops short of explicitly distinguishing itself from the other write siblings (comment_fix, report_fix_result, report_outcome), which is the remaining ambiguity.

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?

'Contribute a reproducible fix' implies the trigger, and 'Fill confirm / not_when / principle / verify / rollback' hints at the expected content shape. However, there is no explicit when-to-use vs when-not guidance, and no routing against the sibling reporting tools that also write fix-related data.

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