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

Beyond the annotations, the description discloses network dependence, GitHub write behavior conditional on open_pr, the return payload (root cause, confidence, model, pull_request_url), and the failure contract ('codna_fix error: ...' text, tool never raises). This is substantially more behavioral context than the annotations alone provide, and it does not contradict any annotation.

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 dense but well structured: purpose first, then prerequisites/offline truth, then return values and failure behavior. Every sentence carries operational weight, and the most important constraints (network, writes, failure mode) are front-loaded.

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 complex tool with auth requirements, network calls, conditional GitHub writes, offline sibling alternatives, an output schema, and special failure behavior, the description covers all key non-schema context. The output schema handles return details, so nothing critical is missing for an agent to invoke this tool 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?

Schema description coverage is 100%, and each parameter already has detailed descriptions covering defaults, required conditions, and side effects. The description adds general context like auth and output shape but not new per-parameter semantics, so the baseline score 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 opens with a specific verb and resource ('Find and fix a bug') and immediately clarifies the full scope: running the Codna agent, engine, and risk simulation. It also distinguishes itself from fully-offline siblings by naming codna_triage, codna_secure, and codna_recall as offline alternatives, so an agent can separate fix behavior from triage/recall/secure.

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 explicit usage context: it requires codna login and a provider key, explains that planning needs network access, and states that only open_pr=true writes to GitHub. It also points to the fully-offline sibling tools as alternatives when offline behavior is required, which is clear when-to-use vs when-not-to-use 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 already mark readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral context: zero LLM tokens/network calls, auto-index on first use, storage outside git, login requirement, and the explicit failure-mode contract ('never raises', returns error text). This goes well beyond the structured 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?

The description is organized in clear blocks: core purpose, usage guidance, parameter list, return format, and failure modes. While long, every sentence adds value and the critical scoping statement is front-loaded. No filler or redundancy.

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?

Given the tool's complexity (5 params, setup requirements, failure modes), the description covers everything an agent needs: return JSON shape, error handling, login flow, and default behaviors. The output schema exists but the description still summarizes the return structure, making it self-sufficient.

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%, so the description is the sole source of parameter meaning. It explains every parameter with concrete semantics: repo (path/URL, default), query (required, empty error), service (scoping), language (filter), final_k (count, default). This fully compensates for the schema's bare titles.

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 opens with a clear, specific verb and resource: 'Recall relevant code from the local on-device Telys memory' with the mechanism 'semantic + lexical search'. It explicitly differentiates from codna_triage by contrasting 'code behind a concept' vs 'whole-repo map', so an agent can distinguish siblings without inspecting schemas.

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 provides explicit guidance on when to use it ('Use when you need the code behind a concept... and when you want it offline') and names the alternative (codna_triage). It also covers prerequisites like first-use login and the default repo behavior, leaving no ambiguity about invocation context.

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 carry only generic flags (readOnly=false, destructive=false), so the description carries the behavioral burden — and it delivers: auth prerequisites, the GitHub-token-dependent auto-filing path with a pre-filled URL fallback, the redaction guarantee ('no secret values'), and consistency with the CLI ('same shape of issue codna report does'). No contradiction with readOnlyHint=false, since filing a report is a 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?

Every sentence earns its place: purpose, sibling boundary, prerequisites, one labeled line per parameter, and return behavior. The core purpose is front-loaded and the parameter block is scannable; the only minor blemish is the repeated 'free' in the license note.

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 4-parameter mutation tool: it covers selection (purpose and sibling routing), invocation (parameter semantics), prerequisites (login and GitHub token), and fallback behavior, and it even describes the return value (issue URL vs pre-filled URL) despite an output schema already existing.

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 description fully compensates. It adds meaning to all four parameters: a worked example for title, guidance on body detail, an explicit enumeration of valid product values ('algenta, codna, telys, sqai, accounts, docs') that the schema lacks (no enums defined), and a privacy/redaction note for include_diagnostics.

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 opening line states a specific verb and resource — 'File a report to thyn-ai/feedback' — and identifies the tool as the public front door for the four products. It also distinguishes itself from a sibling: 'It only files the issue — codna_fix is the one that can open a PR with the fix.'

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 says when to use the tool (to file a report/issue), names the alternative for a different goal (codna_fix for a PR), and lists prerequisites: the one-time codna login device authorization and the GitHub token required for auto-filing, including the offline/no-token fallback to a pre-filled URL.

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 give readOnlyHint, openWorldHint=false, idempotentHint. The description adds rich context beyond those: deterministic, 0 LLM tokens, repo never scanned, agent sidecar never starts, one-time codna login device authorization required and fully offline thereafter, and all failures returned as 'codna_secure error: ...' text with no raising. No contradiction — read-only matches, openWorld=false matches the no-scan claim, idempotent matches deterministic.

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?

Purpose is front-loaded in the first sentence. Three dense paragraphs each earn their place — core purpose/traits, input requirements/error contract, auth prerequisite — with no dead weight. Slightly verbose but tightly structured.

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?

Output schema exists, so return format is covered. The description covers inputs, failure modes, auth, determinism, and absence of side effects. Nothing an agent needs to invoke it correctly is missing; complexity (SARIF ingestion + classification) is well matched by the description.

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 adds genuine value: sarif_path is REQUIRED with no auto-discovery or fallback, SARIF provenance must be complete or the report is rejected, and repo is echoed only for traceability while never being scanned. These constraints go beyond what the schema states.

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 a specific verb+resource: 'Prove which scanner findings are reachable,' then details exact mechanics — ingests a SARIF 2.1.0 report (CodeQL/Semgrep/Snyk/Trivy), classifies each finding into four explicit categories, and reports autofix-eligibility. Unambiguous and clearly distinct from the fix/triage/report/recall siblings, establishing this as the read-only analysis step.

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 ('reports which are autofix-eligible' hints at running before codna_fix) but never explicit. No sibling is named and no when-to-use vs. when-not conditions are given; alternative routing is left to inference. Error behavior and auth prerequisites are documented, but those are behavioral, 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?

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds meaningful behavioral context beyond those annotations: it requires a one-time 'codna login' device authorization, is 'fully offline thereafter,' and produces '0 LLM tokens,' clarifying the tool's resource and connectivity profile. No contradiction exists between the description and 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?

The description is compact and front-loaded: the core purpose appears in the first sentence, followed by sibling contrast, auth prerequisite, parameters, and output summary. Every segment earns its place; there is no filler or repetitive restating of schema fields.

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 read-only tool with an output schema, the description is complete enough: it covers purpose, sibling alternatives, login requirement, offline behavior, input meanings, and return shape. The optional output schema covers return details, so nothing critical is missing for an agent to invoke it 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?

Schema description coverage is 0%, so the description bears the full burden, and it largely succeeds: repo is explained as 'a local path or a git URL (default: current directory),' and issue as 'optional description of what you're looking for.' The repo semantics are strong; the issue semantics are functional but somewhat terse, so a small gap remains in explaining what constitutes a useful issue input.

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 states a specific activity and resource: 'Understand a repository and locate the code relevant to an issue,' with a concrete output ('suspect files + the context-reduction'). It explicitly differentiates from sibling tools by labeling codna_fix as 'plans/acts on one bug' and codna_recall as 'retrieves stored code memory,' while positioning triage as the 'zero-token map + suspect-file list you run first.' This distinguishes the tool clearly.

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 clear usage context: triage is 'the... list you run first,' and codna_fix and codna_recall are named with their differing roles, so an agent can select this tool before acting. It also flags the one-time login prerequisite. It does not explicitly state when not to use triage or mention codna_report_bug/codna_secure, so it falls just short of fully explicit when/when-not guidance.

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